# tensor.news — full data digest

Machine-readable summary of every tracked entity. Human pages: https://tensor.news

## Benchmark Integrity Index

### APEX-Agents — A (100/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3.5 Flash — 49.6 (unverified)
2. Claude Fable 5 — 45 (unverified)
3. Claude Opus 4.8 — 42.5 (unverified)
4. GPT-5.5 — 38.4 (unverified)
5. GPT-5.4 — 35.9 (unverified)
URL: https://tensor.news/benchmarks/apex-agents

### Chess Puzzles — A (100/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.5 Pro — 64 (reproduced)
2. GPT-5.4 Pro — 58.6 (reproduced)
3. Gemini 3.1 Pro — 55 (reproduced)
4. GPT-5.5 — 54 (reproduced)
5. Gemini 3.5 Flash — 50 (reproduced)
URL: https://tensor.news/benchmarks/chess-puzzles

### HLE — A (100/100)
Harness: consistent harness. Test-set privacy: public.
1. Gemini 3.1 Pro — 43.74 (unverified)
2. GPT-5.4 Pro — 41.51 (unverified)
3. Muse Spark — 37.56 (unverified)
4. Gemini 3 Pro — 34.37 (unverified)
5. GPT-5.4 — 33.03 (unverified)
URL: https://tensor.news/benchmarks/hle

### SimpleQA Verified — A (100/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3.1 Pro — 77.3 (reproduced)
2. Gemini 3 Pro — 72.9 (reproduced)
3. Gemini 3.5 Flash — 68.4 (reproduced)
4. Claude Fable 5 — 68.3 (reproduced)
5. Qwen3-Max — 67.47 (reproduced)
URL: https://tensor.news/benchmarks/simpleqa-verified

### ARC-AGI-2 — A (99/100)
Harness: consistent harness. Test-set privacy: held-out.
1. GPT-5.5 — 85 (unverified)
2. GPT-5.5 Pro — 84.58 (unverified)
3. GPT-5.4 Pro — 83.33 (unverified)
4. Gemini 3.1 Pro — 77.1 (unverified)
5. Claude Opus 4.7 — 75.8 (unverified)
URL: https://tensor.news/benchmarks/arc-agi-2

### FrontierMath-2025-02-28-Private — A (99/100)
Harness: consistent harness. Test-set privacy: held-out.
1. Muse Spark — 68.42 (reproduced)
2. Gemini 3 Pro — 65.96 (reproduced)
3. GLM-5.1 — 58.68 (reproduced)
4. Claude Sonnet 4.6 — 56.84 (reproduced)
5. GPT-5.1 — 54.45 (reproduced)
URL: https://tensor.news/benchmarks/frontiermath-2025-02-28-private

### FrontierMath-Tier-4-v2-Private — A (99/100)
Harness: consistent harness. Test-set privacy: held-out.
1. Claude Fable 5 — 87.8 (reproduced)
2. GPT-5.5 Pro — 78.05 (reproduced)
3. GPT-5.5 — 72.5 (reproduced)
4. GPT-5.4 Pro — 58.54 (reproduced)
5. Claude Opus 4.8 — 56.1 (reproduced)
URL: https://tensor.news/benchmarks/frontiermath-tier-4-v2-private

### CadEval — A (98/100)
Harness: consistent harness. Test-set privacy: unknown.
1. o3 — 74 (unverified)
2. Gemini 2.5 Pro (Mar 2025) — 64 (unverified)
3. o4-mini — 62 (unverified)
4. o1 — 56 (unverified)
5. Claude 3.7 Sonnet — 54 (unverified)
URL: https://tensor.news/benchmarks/cadeval

### CursorBench — A (98/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Fable 5 — 72.9 (unverified)
2. Claude Opus 4.7 — 64.8 (unverified)
3. GPT-5.5 — 64.3 (unverified)
4. Claude Opus 4.8 — 63.8 (unverified)
5. GLM-5.2 — 54.6 (unverified)
URL: https://tensor.news/benchmarks/cursorbench

### FrontierMath-Tiers-1-3-v2-Private — A (98/100)
Harness: consistent harness. Test-set privacy: held-out.
1. GPT-5.5 Pro — 87.72 (reproduced)
2. Claude Fable 5 — 87.02 (reproduced)
3. GPT-5.5 — 85.26 (reproduced)
4. GPT-5.4 Pro — 82.46 (reproduced)
5. Claude Opus 4.8 — 80 (reproduced)
URL: https://tensor.news/benchmarks/frontiermath-tiers-1-3-v2-private

### GBAEval — A (98/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Fable 5 — 74.47 (unverified)
2. Claude Opus 4.8 — 70.9 (unverified)
3. GPT-5.5 — 53.22 (unverified)
4. Claude Sonnet 4.6 — 48.76 (unverified)
5. Claude Opus 4.6 — 44.12 (unverified)
URL: https://tensor.news/benchmarks/gbaeval

### GDPval — A (98/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.2 — 49.7 (unverified)
2. Claude Opus 4.5 — 45.5 (unverified)
3. Claude Opus 4.1 — 43.6 (unverified)
4. Claude Sonnet 4.5 — 42.5 (unverified)
5. Gemini 3 Pro — 40.3 (unverified)
URL: https://tensor.news/benchmarks/gdpval

### FrontierMath-Tier-4-2025-07-01-Private — A (93/100)
Harness: consistent harness. Test-set privacy: held-out.
1. Gemini 3 Pro — 31.25 (reproduced)
2. Muse Spark — 24.33 (reproduced)
3. GLM-5.1 — 20.83 (reproduced)
4. GPT-5.1 — 20.83 (reproduced)
5. Qwen 3.6 Plus — 13.89 (reproduced)
URL: https://tensor.news/benchmarks/frontiermath-tier-4-2025-07-01-private

### CritPt — A (92/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.5 Pro — 30.57 (unverified)
2. GPT-5.4 Pro — 30 (unverified)
3. Claude Fable 5 — 28.57 (unverified)
4. GPT-5.5 — 27.14 (unverified)
5. GPT-5.4 — 23.43 (unverified)
URL: https://tensor.news/benchmarks/critpt

### The Agent Company — A (92/100)
Harness: consistent harness. Test-set privacy: unknown.
1. DeepSeek-V3.2-Exp — 42.9 (unverified)
2. Gemini 2.5 Flash (Sep 2025) — 41.1 (unverified)
3. Claude Sonnet 4 — 33.1 (unverified)
4. Claude 3.7 Sonnet — 30.9 (unverified)
5. Gemini 2.5 Pro (May 2025) — 30.3 (unverified)
URL: https://tensor.news/benchmarks/the-agent-company

### GSO-Bench — A (90/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Opus 4.7 — 44.12 (unverified)
2. Claude Opus 4.6 — 41.2 (unverified)
3. GPT-5.5 — 40.2 (unverified)
4. GPT-5.4 — 31.37 (unverified)
5. GPT-5.2 — 27.4 (unverified)
URL: https://tensor.news/benchmarks/gso-bench

### Balrog — A (89/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3 Pro — 58.1 (unverified)
2. Gemini 3.1 Pro — 57 (unverified)
3. Gemini 3 Flash — 48.1 (unverified)
4. Grok 4 — 43.6 (unverified)
5. Claude Opus 4.5 — 43.5 (unverified)
URL: https://tensor.news/benchmarks/balrog

### ExploitBench — A (89/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.5 — 41 (unverified)
2. Claude Opus 4.7 — 28 (unverified)
3. Gemini 3.1 Pro — 26 (unverified)
4. Claude Sonnet 4.6 — 24 (unverified)
5. Kimi K2.6 — 18 (unverified)
URL: https://tensor.news/benchmarks/exploitbench

### GeoBench — A (89/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3 Flash — 88 (unverified)
2. Gemini 2.5 Pro (May 2025) — 86 (unverified)
3. Gemini 3 Pro — 84 (unverified)
4. GPT-5 — 81 (unverified)
5. Gemini 2.5 Pro (Mar 2025) — 81 (unverified)
URL: https://tensor.news/benchmarks/geobench

### PostTrainBench — A (89/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GLM-5.2 — 34.29 (unverified)
2. Claude Opus 4.8 — 34.08 (unverified)
3. Claude Opus 4.7 — 28.56 (unverified)
4. GPT-5.5 — 25.02 (unverified)
5. Claude Opus 4.6 — 24.82 (unverified)
URL: https://tensor.news/benchmarks/posttrainbench

### OTIS Mock AIME 2024-2025 — A (88/100)
Harness: consistent harness. Test-set privacy: unknown. Saturated.
1. GPT-5.5 — 100 (reproduced)
2. GPT-5.5 Pro — 100 (reproduced)
3. Claude Fable 5 — 99.72 (reproduced)
4. Claude Opus 4.8 — 98.33 (reproduced)
5. Claude Opus 4.7 — 97.8 (reproduced)
URL: https://tensor.news/benchmarks/otis-mock-aime-2024-2025

### WeirdML — A (88/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Fable 5 — 87.85 (unverified)
2. GPT-5.5 — 84.91 (unverified)
3. Claude Opus 4.8 — 82.89 (unverified)
4. GPT-5.3 Codex — 79.3 (unverified)
5. Claude Opus 4.6 — 77.95 (unverified)
URL: https://tensor.news/benchmarks/weirdml

### Aider polyglot — A (87/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5 — 88 (unverified)
2. o3-pro — 84.9 (unverified)
3. Gemini 2.5 Pro (Jun 2025) — 83.1 (unverified)
4. o3 — 81.3 (unverified)
5. Grok 4 — 79.6 (unverified)
URL: https://tensor.news/benchmarks/aider-polyglot

### Fiction.LiveBench — A (87/100)
Harness: consistent harness. Test-set privacy: unknown.
1. o3-pro — 97.2 (unverified)
2. GPT-5 — 97.2 (unverified)
3. Grok 4 — 94.4 (unverified)
4. Grok 4 Fast — 94.4 (unverified)
5. Gemini 2.5 Pro (Jun 2025) — 91.7 (unverified)
URL: https://tensor.news/benchmarks/fiction-livebench

### VPCT — A (87/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3 Pro — 86.5 (unverified)
2. GPT-5.2 — 76 (unverified)
3. Gemini 3 Flash — 58.9 (unverified)
4. GPT-5 — 49 (unverified)
5. GPT-5.1 — 38.05 (unverified)
URL: https://tensor.news/benchmarks/vpct

### SimpleBench — A (86/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Fable 5 — 78.28 (unverified)
2. Gemini 3.1 Pro — 75.52 (unverified)
3. GPT-5.5 Pro — 72.28 (unverified)
4. Gemini 3.5 Flash — 72.04 (unverified)
5. Gemini 3 Pro — 71.68 (unverified)
URL: https://tensor.news/benchmarks/simplebench

### Terminal Bench — B (84/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Opus 4.7 — 90.2 (unverified)
2. GPT-5.5 — 84.7 (unverified)
3. GPT-5.4 — 81.8 (unverified)
4. Gemini 3.1 Pro — 80.2 (unverified)
5. Claude Opus 4.6 — 79.8 (unverified)
URL: https://tensor.news/benchmarks/terminal-bench

### SWE-Bench verified — B (83/100)
Harness: consistent harness. Test-set privacy: public.
1. Claude Opus 4.7 — 83.47 (reproduced)
2. GPT-5.5 — 80.58 (reproduced)
3. Gemini 3.5 Flash — 79.34 (reproduced)
4. Claude Opus 4.6 — 78.72 (reproduced)
5. GLM-5.2 — 78.7 (reproduced)
URL: https://tensor.news/benchmarks/swe-bench-verified

### CL-bench — B (82/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.4 — 27.9 (unverified)
2. GPT-5.1 — 23.7 (unverified)
3. Grok 4.20 — 22.2 (unverified)
4. Claude Opus 4.5 — 21.1 (unverified)
5. Gemini 3.1 Pro — 20.8 (unverified)
URL: https://tensor.news/benchmarks/cl-bench

### CL-bench Life — B (81/100)
Harness: consistent harness. Test-set privacy: unknown.
1. GPT-5.5 — 22.2 (unverified)
2. GPT-5.4 — 21.7 (unverified)
3. GPT-5.1 — 17.3 (unverified)
4. Claude Opus 4.6 — 17 (unverified)
5. Gemini 3.1 Pro — 16.9 (unverified)
URL: https://tensor.news/benchmarks/cl-bench-life

### GPQA diamond — B (81/100)
Harness: consistent harness. Test-set privacy: public.
1. GPT-5.4 Pro — 92.8 (reproduced)
2. Gemini 3.1 Pro — 92.13 (reproduced)
3. GPT-5.5 — 92 (reproduced)
4. GPT-5.5 Pro — 91.9 (reproduced)
5. GPT-5.4 — 91.07 (reproduced)
URL: https://tensor.news/benchmarks/gpqa-diamond

### OSWorld 2.0 — B (81/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Opus 4.8 — 20.6 (unverified)
2. Claude Opus 4.7 — 18.2 (unverified)
3. GPT-5.5 — 13 (unverified)
4. Claude Sonnet 4.6 — 9.3 (unverified)
5. Kimi K2.6 — 4.6 (unverified)
URL: https://tensor.news/benchmarks/osworld-2-0

### Remote Labor Index — B (81/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Fable 5 — 16.1 (unverified)
2. Claude Opus 4.8 — 8.33 (unverified)
3. Claude Opus 4.6 — 4.17 (unverified)
4. Claude Opus 4.5 — 3.75 (unverified)
5. GPT-5.2 — 2.5 (unverified)
URL: https://tensor.news/benchmarks/remote-labor-index

### OSWorld — B (80/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Sonnet 4.6 — 72.1 (unverified)
2. Claude Opus 4.5 — 66.3 (unverified)
3. Kimi K2.5 — 63.3 (unverified)
4. Claude Sonnet 4.5 — 62.9 (unverified)
5. Claude Sonnet 4 — 43.9 (unverified)
URL: https://tensor.news/benchmarks/osworld

### Cybench — B (79/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. Claude Opus 4.6 — 93 (self-reported)
2. Claude Opus 4.5 — 82 (self-reported)
3. Claude Sonnet 4.5 — 60 (self-reported)
4. Grok 4 — 43 (self-reported)
5. Claude Opus 4.1 — 42 (unverified)
URL: https://tensor.news/benchmarks/cybench

### DeepResearch Bench — B (78/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Claude Opus 4.6 — 55.31 (unverified)
2. GPT-5 — 55.13 (unverified)
3. Claude Sonnet 4.6 — 54.87 (unverified)
4. GPT-5.5 — 54.01 (unverified)
5. Claude Sonnet 4.5 — 52.6 (unverified)
URL: https://tensor.news/benchmarks/deepresearch-bench

### Lech Mazur Writing — B (76/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Kimi K2 (Sep 2025) — 87.29 (unverified)
2. GPT-5 — 87.23 (unverified)
3. Qwen3-Max — 87.11 (unverified)
4. Kimi K2 (Jul 2025) — 86.93 (unverified)
5. o3-pro — 86.28 (unverified)
URL: https://tensor.news/benchmarks/lech-mazur-writing

### ARC-AGI — B (74/100)
Harness: consistent harness. Test-set privacy: unknown.
1. Gemini 3.1 Pro — 98 (unverified)
2. GPT-5.5 Pro — 96.5 (unverified)
3. GPT-5.5 — 95 (unverified)
4. GPT-5.4 Pro — 94.5 (unverified)
5. Claude Opus 4.6 — 94 (unverified)
URL: https://tensor.news/benchmarks/arc-agi

### MATH level 5 — B (73/100)
Harness: consistent harness. Test-set privacy: public. Saturated.
1. GPT-5 — 98.13 (reproduced)
2. GPT-5 mini — 97.85 (reproduced)
3. o4-mini — 97.83 (reproduced)
4. o3 — 97.77 (reproduced)
5. Claude Sonnet 4.5 — 97.73 (reproduced)
URL: https://tensor.news/benchmarks/math-level-5

### BBH — B (71/100)
Harness: mixed harness — not directly comparable. Test-set privacy: public.
1. Gemini 1.5 Pro (May 2024) — 85.6 (unverified)
2. DeepSeek-V3 — 83.33 (self-reported)
3. Llama 3.1-405B — 77.2 (self-reported)
4. phi-3-medium 14B — 75.2 (self-reported)
5. Qwen2.5-72B — 73.07 (self-reported)
URL: https://tensor.news/benchmarks/bbh

### GSM8K — C (69/100)
Harness: mixed harness — not directly comparable. Test-set privacy: public.
1. GPT-4 (Mar 2023) — 92 (self-reported)
2. GPT-4o mini — 91.3 (self-reported)
3. Qwen2.5-Coder-32B — 91.1 (self-reported)
4. GPT-4 (Jun 2023) — 89.99 (unverified)
5. Qwen2.5-Coder-14B — 88.7 (self-reported)
URL: https://tensor.news/benchmarks/gsm8k

### ScienceQA — C (68/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. GPT-4o (May 2024) — 84.67 (self-reported)
2. Claude 3 Haiku — 62.67 (self-reported)
3. Llama 2-13B — 41.04 (unverified)
4. LLaMA-13B — 24.44 (unverified)
5. Llama 2-7B — 24.11 (unverified)
URL: https://tensor.news/benchmarks/scienceqa

### HellaSwag — C (67/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. GPT-4 (Mar 2023) — 93.73 (unverified)
2. Llama 3.1-405B — 85.6 (self-reported)
3. Falcon-180B — 85.33 (unverified)
4. DeepSeek-V3 — 85.2 (self-reported)
5. DeepSeek-V2 (MoE-236B, May 2024) — 82.8 (self-reported)
URL: https://tensor.news/benchmarks/hellaswag

### MMLU — C (67/100)
Harness: mixed harness — not directly comparable. Test-set privacy: public.
1. GPT-4o (Nov 2024) — 84.13 (self-reported)
2. Claude 3.5 Sonnet (October 2024) — 83.07 (unverified)
3. DeepSeek-V3 — 82.93 (unverified)
4. Gemini 1.5 Pro (Sept 2024) — 82.53 (unverified)
5. Claude 3.5 Sonnet — 82 (unverified)
URL: https://tensor.news/benchmarks/mmlu

### ARC AI2 — C (66/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. Llama 3.1-405B — 93.73 (self-reported)
2. DeepSeek-V3 — 93.73 (self-reported)
3. Qwen2.5-72B — 92.67 (self-reported)
4. DeepSeek-V2 (MoE-236B, May 2024) — 89.6 (self-reported)
5. phi-3-medium 14B — 88.8 (self-reported)
URL: https://tensor.news/benchmarks/arc-ai2

### TriviaQA — C (63/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. Llama 2-70B — 87.6 (unverified)
2. Claude 2 — 87.5 (self-reported)
3. PaLM 2-L — 86.1 (self-reported)
4. LLaMA-65B — 86 (unverified)
5. GPT-3.5 Turbo (Nov 2023) — 85.8 (self-reported)
URL: https://tensor.news/benchmarks/triviaqa

### PIQA — C (62/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. PowerMoE-3b — 79.1 (unverified)
2. GPT-4o mini — 77.4 (self-reported)
3. Gemini 1.5 Flash (Sep 2024) — 75 (self-reported)
4. Llama 3.1-405B — 71.8 (self-reported)
5. Falcon-180B — 69.8 (unverified)
URL: https://tensor.news/benchmarks/piqa

### Winogrande — C (62/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. Llama 3.1-405B — 78.4 (unverified)
2. Claude 3 Opus — 77 (unverified)
3. GPT-4 (Mar 2023) — 75 (self-reported)
4. Falcon-180B — 74.2 (unverified)
5. DeepSeek-V2 (MoE-236B, May 2024) — 72.6 (self-reported)
URL: https://tensor.news/benchmarks/winogrande

### OpenBookQA — C (61/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. phi-3-mini 3.8B — 84 (self-reported)
2. phi-3-small 7.4B — 84 (self-reported)
3. phi-3-medium 14B — 83.2 (self-reported)
4. GPT-3.5 Turbo (Nov 2023) — 81.33 (self-reported)
5. Mixtral 8x7B — 81.07 (self-reported)
URL: https://tensor.news/benchmarks/openbookqa

### ANLI — C (59/100)
Harness: consistent harness. Test-set privacy: unknown.
1. phi-3-small 7.4B — 37.15 (self-reported)
2. GPT-3.5 Turbo (Nov 2023) — 37.15 (self-reported)
3. Llama 3-8B — 35.95 (self-reported)
4. phi-3-medium 14B — 33.7 (self-reported)
5. Mixtral 8x7B — 32.8 (self-reported)
URL: https://tensor.news/benchmarks/anli

### LAMBADA — D (54/100)
Harness: mixed harness — not directly comparable. Test-set privacy: unknown.
1. Falcon-180B — 79.8 (unverified)
2. Llama 2-70B — 78.9 (self-reported)
3. LLaMA-65B — 77.7 (self-reported)
4. Falcon-40B — 77.3 (unverified)
5. LLaMA-33B — 77.2 (self-reported)
URL: https://tensor.news/benchmarks/lambada

## Model Claim Ledger summary

- unverified: 1048
- independently_reproduced: 573
- self_reported: 322

## All entity pages

### Models
- https://tensor.news/models/qwen-qwen3-0-6b — Qwen3-0.6B
- https://tensor.news/models/qwen-qwen3-8b — Qwen3-8B
- https://tensor.news/models/facebook-opt-125m — opt-125m
- https://tensor.news/models/openai-community-gpt2 — gpt2
- https://tensor.news/models/qwen-qwen2-5-7b-instruct — Qwen2.5-7B-Instruct
- https://tensor.news/models/qwen-qwen2-5-1-5b-instruct — Qwen2.5-1.5B-Instruct
- https://tensor.news/models/trl-internal-testing-tiny-qwen2forcausallm-2-5 — tiny-Qwen2ForCausalLM-2.5
- https://tensor.news/models/qwen-qwen3-4b — Qwen3-4B
- https://tensor.news/models/meta-llama-llama-3-2-1b-instruct — Llama-3.2-1B-Instruct
- https://tensor.news/models/meta-llama-llama-3-1-8b-instruct — Llama-3.1-8B-Instruct
- https://tensor.news/models/deepseek-ai-deepseek-r1 — DeepSeek-R1
- https://tensor.news/models/nvidia-qwen3-6-35b-a3b-nvfp4 — Qwen3.6-35B-A3B-NVFP4
- https://tensor.news/models/openai-gpt-oss-20b — gpt-oss-20b
- https://tensor.news/models/antirez-deepseek-v4-gguf — deepseek-v4-gguf
- https://tensor.news/models/qwen-qwen2-5-3b-instruct — Qwen2.5-3B-Instruct
- https://tensor.news/models/qwen-qwen3-32b — Qwen3-32B
- https://tensor.news/models/qwen-qwen3-1-7b — Qwen3-1.7B
- https://tensor.news/models/qwen-qwen3-4b-instruct-2507 — Qwen3-4B-Instruct-2507
- https://tensor.news/models/hmellor-tiny-random-llamaforcausallm — tiny-random-LlamaForCausalLM
- https://tensor.news/models/qwen-qwen2-5-0-5b-instruct — Qwen2.5-0.5B-Instruct
- https://tensor.news/models/dphn-dolphin-2-9-1-yi-1-5-34b — dolphin-2.9.1-yi-1.5-34b
- https://tensor.news/models/openai-gpt-oss-120b — gpt-oss-120b
- https://tensor.news/models/qwen-qwen3-14b — Qwen3-14B
- https://tensor.news/models/google-gemma-3-1b-it — gemma-3-1b-it
- https://tensor.news/models/qwen-qwen2-5-coder-14b-instruct — Qwen2.5-Coder-14B-Instruct
- https://tensor.news/models/google-gemma-3-270m — gemma-3-270m
- https://tensor.news/models/qwen-qwen2-5-7b-instruct-awq — Qwen2.5-7B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen2-1-5b-instruct — Qwen2-1.5B-Instruct
- https://tensor.news/models/distilbert-distilgpt2 — distilgpt2
- https://tensor.news/models/eleutherai-pythia-160m — pythia-160m
- https://tensor.news/models/qwen-qwen2-5-32b-instruct — Qwen2.5-32B-Instruct
- https://tensor.news/models/qwen-qwen3-30b-a3b — Qwen3-30B-A3B
- https://tensor.news/models/farbodtavakkoli-otel-llm-e4b-it — OTel-LLM-E4B-IT
- https://tensor.news/models/zai-org-glm-4-7-flash — GLM-4.7-Flash
- https://tensor.news/models/qwen-qwen3-coder-next-fp8 — Qwen3-Coder-Next-FP8
- https://tensor.news/models/huggingfacetb-smollm2-135m-instruct — SmolLM2-135M-Instruct
- https://tensor.news/models/deepseek-ai-deepseek-v4-flash — DeepSeek-V4-Flash
- https://tensor.news/models/qwen-qwen2-5-14b-instruct — Qwen2.5-14B-Instruct
- https://tensor.news/models/tinyllama-tinyllama-1-1b-chat-v1-0 — TinyLlama-1.1B-Chat-v1.0
- https://tensor.news/models/meta-llama-llama-3-2-3b-instruct — Llama-3.2-3B-Instruct
- https://tensor.news/models/qwen-qwen2-5-0-5b — Qwen2.5-0.5B
- https://tensor.news/models/andycurrent-gemma-3-1b-it-glm-4-7-flash-heretic-uncensored-thinking-gguf — Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking_GGUF
- https://tensor.news/models/nvidia-gemma-4-26b-a4b-nvfp4 — Gemma-4-26B-A4B-NVFP4
- https://tensor.news/models/qwen-qwen2-5-coder-7b-instruct — Qwen2.5-Coder-7B-Instruct
- https://tensor.news/models/zai-org-glm-5-fp8 — GLM-5-FP8
- https://tensor.news/models/zai-org-glm-5-2-fp8 — GLM-5.2-FP8
- https://tensor.news/models/deepseek-ai-deepseek-v3-2 — DeepSeek-V3.2
- https://tensor.news/models/deepseek-ai-deepseek-r1-0528 — DeepSeek-R1-0528
- https://tensor.news/models/qwen-qwen3-14b-awq — Qwen3-14B-AWQ
- https://tensor.news/models/qwen-qwen2-5-coder-32b-instruct-awq — Qwen2.5-Coder-32B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen3-0-6b-fp8 — Qwen3-0.6B-FP8
- https://tensor.news/models/meta-llama-llama-3-2-1b — Llama-3.2-1B
- https://tensor.news/models/qwen-qwen3-32b-awq — Qwen3-32B-AWQ
- https://tensor.news/models/ibm-research-powermoe-3b — PowerMoE-3b
- https://tensor.news/models/qwen-qwen3-coder-30b-a3b-instruct — Qwen3-Coder-30B-A3B-Instruct
- https://tensor.news/models/nvidia-diffusiongemma-26b-a4b-it-nvfp4 — diffusiongemma-26B-A4B-it-NVFP4
- https://tensor.news/models/nvidia-gemma-4-31b-it-nvfp4 — Gemma-4-31B-IT-NVFP4
- https://tensor.news/models/redhatai-llama-3-2-1b-instruct-fp8-dynamic — Llama-3.2-1B-Instruct-FP8-dynamic
- https://tensor.news/models/nvidia-nvidia-nemotron-3-nano-4b-bf16 — NVIDIA-Nemotron-3-Nano-4B-BF16
- https://tensor.news/models/apple-openelm-1-1b-instruct — OpenELM-1_1B-Instruct
- https://tensor.news/models/deepseek-ai-deepseek-r1-0528-qwen3-8b — DeepSeek-R1-0528-Qwen3-8B
- https://tensor.news/models/meta-llama-llama-3-1-8b — Llama-3.1-8B
- https://tensor.news/models/huggingfacetb-smollm2-135m — SmolLM2-135M
- https://tensor.news/models/qwen-qwen2-5-14b-instruct-awq — Qwen2.5-14B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen3-coder-30b-a3b-instruct-fp8 — Qwen3-Coder-30B-A3B-Instruct-FP8
- https://tensor.news/models/nvidia-nvidia-nemotron-3-nano-30b-a3b-nvfp4 — NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
- https://tensor.news/models/quanttrio-qwen3-vl-30b-a3b-instruct-awq — Qwen3-VL-30B-A3B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen2-5-coder-32b-instruct — Qwen2.5-Coder-32B-Instruct
- https://tensor.news/models/meta-llama-meta-llama-3-8b-instruct — Meta-Llama-3-8B-Instruct
- https://tensor.news/models/meta-llama-meta-llama-3-8b — Meta-Llama-3-8B
- https://tensor.news/models/nvidia-nvidia-nemotron-3-super-120b-a12b-nvfp4 — NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
- https://tensor.news/models/qwen-qwen3-coder-next — Qwen3-Coder-Next
- https://tensor.news/models/qwen-qwen3-30b-a3b-instruct-2507 — Qwen3-30B-A3B-Instruct-2507
- https://tensor.news/models/nvidia-nvidia-nemotron-3-super-120b-a12b-bf16 — NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- https://tensor.news/models/openai-community-gpt2-large — gpt2-large
- https://tensor.news/models/qwen-qwen2-0-5b — Qwen2-0.5B
- https://tensor.news/models/deepseek-ai-deepseek-v4-pro — DeepSeek-V4-Pro
- https://tensor.news/models/deepseek-ai-deepseek-v2-lite-chat — DeepSeek-V2-Lite-Chat
- https://tensor.news/models/h2oai-h2ovl-mississippi-800m — h2ovl-mississippi-800m
- https://tensor.news/models/minimaxai-minimax-m2-7 — MiniMax-M2.7
- https://tensor.news/models/meta-llama-llama-3-1-70b-instruct — Llama-3.1-70B-Instruct
- https://tensor.news/models/h2oai-h2ovl-mississippi-2b — h2ovl-mississippi-2b
- https://tensor.news/models/moonshotai-kimi-k2-instruct-0905 — Kimi-K2-Instruct-0905
- https://tensor.news/models/qwen-qwen2-5-1-5b — Qwen2.5-1.5B
- https://tensor.news/models/thebloke-tinyllama-1-1b-chat-v0-3-gptq — TinyLlama-1.1B-Chat-v0.3-GPTQ
- https://tensor.news/models/google-gemma-3-270m-it — gemma-3-270m-it
- https://tensor.news/models/sshleifer-tiny-gpt2 — tiny-gpt2
- https://tensor.news/models/nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16 — NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- https://tensor.news/models/deepseek-ai-deepseek-coder-v2-lite-instruct — DeepSeek-Coder-V2-Lite-Instruct
- https://tensor.news/models/qwen-qwen2-5-coder-14b-instruct-awq — Qwen2.5-Coder-14B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen2-5-72b-instruct-awq — Qwen2.5-72B-Instruct-AWQ
- https://tensor.news/models/nvidia-kimi-k2-5-nvfp4 — Kimi-K2.5-NVFP4
- https://tensor.news/models/mistralai-mistral-7b-instruct-v0-2 — Mistral-7B-Instruct-v0.2
- https://tensor.news/models/deepseek-ai-deepseek-v3 — DeepSeek-V3
- https://tensor.news/models/qwen-qwen3-0-6b-base — Qwen3-0.6B-Base
- https://tensor.news/models/nm-testing-smollm-1-7b-instruct-quantized-w4a16 — SmolLM-1.7B-Instruct-quantized.w4a16
- https://tensor.news/models/microsoft-phi-3-5-mini-instruct — Phi-3.5-mini-instruct
- https://tensor.news/models/farbodtavakkoli-otel-llm-8b-a1b-it — OTel-LLM-8B-A1B-IT
- https://tensor.news/models/redhatai-qwen2-5-1-5b-quantized-w8a8 — Qwen2.5-1.5B-quantized.w8a8
- https://tensor.news/models/deepseek-ai-deepseek-v3-0324 — DeepSeek-V3-0324
- https://tensor.news/models/qwen-qwen3-4b-instruct-2507-fp8 — Qwen3-4B-Instruct-2507-FP8
- https://tensor.news/models/eleutherai-pythia-70m-deduped — pythia-70m-deduped
- https://tensor.news/models/qwen-qwen3-235b-a22b — Qwen3-235B-A22B
- https://tensor.news/models/microsoft-phi-tiny-moe-instruct — Phi-tiny-MoE-instruct
- https://tensor.news/models/trl-internal-testing-tiny-gptossforcausallm — tiny-GptOssForCausalLM
- https://tensor.news/models/microsoft-phi-4 — phi-4
- https://tensor.news/models/nvidia-kimi-k2-6-nvfp4 — Kimi-K2.6-NVFP4
- https://tensor.news/models/deepseek-ai-deepseek-r1-distill-qwen-32b — DeepSeek-R1-Distill-Qwen-32B
- https://tensor.news/models/mistralai-mistral-7b-v0-1 — Mistral-7B-v0.1
- https://tensor.news/models/zai-org-glm-5-1-fp8 — GLM-5.1-FP8
- https://tensor.news/models/microsoft-phi-2 — phi-2
- https://tensor.news/models/nvidia-deepseek-r1-0528-nvfp4-v2 — DeepSeek-R1-0528-NVFP4-v2
- https://tensor.news/models/state-spaces-mamba-130m-hf — mamba-130m-hf
- https://tensor.news/models/redhatai-llama-3-2-1b-instruct-fp8 — Llama-3.2-1B-Instruct-FP8
- https://tensor.news/models/qwen-qwen2-5-32b-instruct-awq — Qwen2.5-32B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen2-5-1-5b-instruct-awq — Qwen2.5-1.5B-Instruct-AWQ
- https://tensor.news/models/qwen-qwen2-5-coder-1-5b-instruct — Qwen2.5-Coder-1.5B-Instruct
- https://tensor.news/models/meta-llama-llama-3-3-70b-instruct — Llama-3.3-70B-Instruct
- https://tensor.news/models/minimaxai-minimax-m2-5 — MiniMax-M2.5
- https://tensor.news/models/huggingfacetb-smollm3-3b — SmolLM3-3B
- https://tensor.news/models/trl-internal-testing-tiny-qwen3forcausallm — tiny-Qwen3ForCausalLM
- https://tensor.news/models/qwen-qwen2-7b-instruct — Qwen2-7B-Instruct
- https://tensor.news/models/tiiuae-falcon-7b — falcon-7b
- https://tensor.news/models/meta-llama-llama-2-7b-hf — Llama-2-7b-hf
- https://tensor.news/models/yuxinlu1-gemma-4-12b-coder-fable5-composer2-5-v1-gguf — gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
- https://tensor.news/models/qwen-qwen2-5-72b-instruct — Qwen2.5-72B-Instruct
- https://tensor.news/models/peft-internal-testing-tiny-random-optforcausallm — tiny-random-OPTForCausalLM
- https://tensor.news/models/ibm-granite-granite-4-1-8b — granite-4.1-8b
- https://tensor.news/models/hmellor-tiny-random-gemma2forcausallm — tiny-random-Gemma2ForCausalLM
- https://tensor.news/models/speakleash-bielik-11b-v3-0-instruct-awq — Bielik-11B-v3.0-Instruct-awq
- https://tensor.news/models/deepseek-ai-deepseek-r1-distill-qwen-1-5b — DeepSeek-R1-Distill-Qwen-1.5B
- https://tensor.news/models/deepseek-ai-deepseek-r1-distill-llama-70b — DeepSeek-R1-Distill-Llama-70B
- https://tensor.news/models/meta-llama-llama-3-2-3b — Llama-3.2-3B
- https://tensor.news/models/nvidia-nvidia-nemotron-nano-9b-v2 — NVIDIA-Nemotron-Nano-9B-v2
- https://tensor.news/models/qwen-qwen3-1-7b-base — Qwen3-1.7B-Base
- https://tensor.news/models/cyankiwi-qwen3-30b-a3b-instruct-2507-awq-4bit — Qwen3-30B-A3B-Instruct-2507-AWQ-4bit
- https://tensor.news/models/qwen-qwen3-8b-fp8 — Qwen3-8B-FP8
- https://tensor.news/models/unsloth-qwen2-5-7b-instruct-bnb-4bit — Qwen2.5-7B-Instruct-bnb-4bit
- https://tensor.news/models/trl-internal-testing-tiny-qwen3moeforcausallm — tiny-Qwen3MoeForCausalLM
- https://tensor.news/models/llamafactory-tiny-random-llama-3 — tiny-random-Llama-3
- https://tensor.news/models/microsoft-phi-3-mini-4k-instruct — Phi-3-mini-4k-instruct
- https://tensor.news/models/qwen-qwen3-4b-base — Qwen3-4B-Base
- https://tensor.news/models/prefeitura-rio-rio-3-0-open-mini — Rio-3.0-Open-Mini
- https://tensor.news/models/nvidia-deepseek-v4-flash-nvfp4 — DeepSeek-V4-Flash-NVFP4
- https://tensor.news/models/hugging-quants-llama-3-2-1b-instruct-q8-0-gguf — Llama-3.2-1B-Instruct-Q8_0-GGUF
- https://tensor.news/models/qwen-qwen3-4b-awq — Qwen3-4B-AWQ
- https://tensor.news/models/cyankiwi-hermes-4-14b-awq-4bit — Hermes-4-14B-AWQ-4bit
- https://tensor.news/models/tiger-lab-vlm2vec-full — VLM2Vec-Full
- https://tensor.news/models/nousresearch-meta-llama-3-1-8b-instruct — Meta-Llama-3.1-8B-Instruct
- https://tensor.news/models/trl-internal-testing-tiny-random-llamaforcausallm — tiny-random-LlamaForCausalLM
- https://tensor.news/models/amazon-nova-pro — Amazon Nova Pro
- https://tensor.news/models/claude-3-opus — Claude 3 Opus
- https://tensor.news/models/gemini-3-flash — Gemini 3 Flash
- https://tensor.news/models/gemini-3-pro — Gemini 3 Pro
- https://tensor.news/models/gemini-3-1-flash-lite — Gemini 3.1 Flash-Lite
- https://tensor.news/models/gemini-3-1-pro — Gemini 3.1 Pro
- https://tensor.news/models/gemini-3-5-flash — Gemini 3.5 Flash
- https://tensor.news/models/gemma-2-27b — Gemma 2 27B
- https://tensor.news/models/gemma-2-9b — Gemma 2 9B
- https://tensor.news/models/gemma-2b — Gemma 2B
- https://tensor.news/models/gemma-3-27b — Gemma 3 27B
- https://tensor.news/models/gemma-7b — Gemma 7B
- https://tensor.news/models/claude-3-sonnet — Claude 3 Sonnet
- https://tensor.news/models/grok-3 — Grok 3
- https://tensor.news/models/grok-4 — Grok 4
- https://tensor.news/models/grok-4-fast — Grok 4 Fast
- https://tensor.news/models/grok-4-20 — Grok 4.20
- https://tensor.news/models/grok-4-3-beta — Grok 4.3 Beta
- https://tensor.news/models/grok-2-dec-2024 — Grok-2 (Dec 2024)
- https://tensor.news/models/grok-3-mini — Grok-3 mini
- https://tensor.news/models/intellect-1 — INTELLECT-1
- https://tensor.news/models/claude-3-5-haiku — Claude 3.5 Haiku
- https://tensor.news/models/kimi-k2-jul-2025 — Kimi K2 (Jul 2025)
- https://tensor.news/models/kimi-k2-sep-2025 — Kimi K2 (Sep 2025)
- https://tensor.news/models/kimi-k2-thinking — Kimi K2 Thinking
- https://tensor.news/models/kimi-k2-5 — Kimi K2.5
- https://tensor.news/models/kimi-k2-6 — Kimi K2.6
- https://tensor.news/models/kimi-k2-7-code — Kimi K2.7 Code
- https://tensor.news/models/llama-13b — LLaMA-13B
- https://tensor.news/models/llama-33b — LLaMA-33B
- https://tensor.news/models/llama-65b — LLaMA-65B
- https://tensor.news/models/llama-7b — LLaMA-7B
- https://tensor.news/models/claude-3-5-sonnet — Claude 3.5 Sonnet
- https://tensor.news/models/llama-2-13b — Llama 2-13B
- https://tensor.news/models/llama-2-34b — Llama 2-34B
- https://tensor.news/models/llama-2-70b — Llama 2-70B
- https://tensor.news/models/llama-2-7b — Llama 2-7B
- https://tensor.news/models/llama-3-70b — Llama 3-70B
- https://tensor.news/models/llama-3-8b — Llama 3-8B
- https://tensor.news/models/llama-3-1-405b — Llama 3.1-405B
- https://tensor.news/models/llama-3-1-70b — Llama 3.1-70B
- https://tensor.news/models/llama-3-1-8b — Llama 3.1-8B
- https://tensor.news/models/llama-3-2-90b — Llama 3.2 90B
- https://tensor.news/models/claude-3-5-sonnet-october-2024 — Claude 3.5 Sonnet (October 2024)
- https://tensor.news/models/llama-3-3-70b — Llama 3.3 70B
- https://tensor.news/models/llama-4-maverick — Llama 4 Maverick
- https://tensor.news/models/llama-4-scout — Llama 4 Scout
- https://tensor.news/models/mpt-30b — MPT-30B
- https://tensor.news/models/mpt-7b — MPT-7B
- https://tensor.news/models/magistral-small-1-1 — Magistral Small 1.1
- https://tensor.news/models/minimax-m2-5 — MiniMax-M2.5
- https://tensor.news/models/minimax-m2-7 — MiniMax-M2.7
- https://tensor.news/models/mistral-7b-v0-1 — Mistral 7B v0.1
- https://tensor.news/models/claude-3-7-sonnet — Claude 3.7 Sonnet
- https://tensor.news/models/mistral-large — Mistral Large
- https://tensor.news/models/mistral-large-2-jul-2024 — Mistral Large 2 (Jul 2024)
- https://tensor.news/models/mistral-large-2-nov-2024 — Mistral Large 2 (Nov 2024)
- https://tensor.news/models/mistral-medium-3 — Mistral Medium 3
- https://tensor.news/models/mistral-nemo — Mistral NeMo
- https://tensor.news/models/mistral-small-3-1 — Mistral Small 3.1
- https://tensor.news/models/mixtral-8x22b — Mixtral 8x22B
- https://tensor.news/models/mixtral-8x7b — Mixtral 8x7B
- https://tensor.news/models/muse-spark — Muse Spark
- https://tensor.news/models/nemotron-4-15b — Nemotron-4 15B
- https://tensor.news/models/claude-fable-5 — Claude Fable 5
- https://tensor.news/models/palm-2-l — PaLM 2-L
- https://tensor.news/models/palm-2-m — PaLM 2-M
- https://tensor.news/models/palm-2-s — PaLM 2-S
- https://tensor.news/models/phi-1-5 — Phi-1.5
- https://tensor.news/models/phi-2 — Phi-2
- https://tensor.news/models/phi-4 — Phi-4
- https://tensor.news/models/qwen-3-5-flash-hosted-35b-a3b — Qwen 3.5 Flash (hosted 35B-A3B)
- https://tensor.news/models/claude-haiku-4-5 — Claude Haiku 4.5
- https://tensor.news/models/qwen-3-5-plus-hosted-397b-a17b — Qwen 3.5 Plus (hosted 397B-A17B)
- https://tensor.news/models/qwen-3-6-flash — Qwen 3.6 Flash
- https://tensor.news/models/qwen-3-6-max-preview — Qwen 3.6 Max (Preview)
- https://tensor.news/models/qwen-3-6-plus — Qwen 3.6 Plus
- https://tensor.news/models/qwen-14b — Qwen-14B
- https://tensor.news/models/qwen-1-8b — Qwen-1_8B
- https://tensor.news/models/qwen-7b — Qwen-7B
- https://tensor.news/models/qwen2-72b — Qwen2-72B
- https://tensor.news/models/qwen2-5-72b — Qwen2.5-72B
- https://tensor.news/models/qwen2-5-coder-1-5b — Qwen2.5-Coder (1.5B)
- https://tensor.news/models/claude-instant — Claude Instant
- https://tensor.news/models/qwen2-5-coder-7b — Qwen2.5-Coder (7B)
- https://tensor.news/models/qwen2-5-coder-0-5b — Qwen2.5-Coder-0.5B
- https://tensor.news/models/qwen2-5-coder-14b — Qwen2.5-Coder-14B
- https://tensor.news/models/qwen2-5-coder-32b — Qwen2.5-Coder-32B
- https://tensor.news/models/qwen2-5-coder-3b — Qwen2.5-Coder-3B
- https://tensor.news/models/qwen2-5-max — Qwen2.5-Max
- https://tensor.news/models/qwen3-235b-a22b — Qwen3-235B-A22B
- https://tensor.news/models/qwen3-235b-a22b-instruct-jul-2025 — Qwen3-235B-A22B-Instruct (Jul 2025)
- https://tensor.news/models/qwen3-235b-a22b-thinking-jul-2025 — Qwen3-235B-A22B-Thinking (Jul 2025)
- https://tensor.news/models/qwen3-max — Qwen3-Max
- https://tensor.news/models/claude-opus-4 — Claude Opus 4
- https://tensor.news/models/qwen3-7-max — Qwen3.7-Max
- https://tensor.news/models/redpajama-incite-7b-base — RedPajama-INCITE-7B-Base
- https://tensor.news/models/stable-beluga-2 — Stable Beluga 2
- https://tensor.news/models/starcoder-2-15b — StarCoder 2 15B
- https://tensor.news/models/starcoder-2-3b — StarCoder 2 3B
- https://tensor.news/models/starcoder-2-7b — StarCoder 2 7B
- https://tensor.news/models/xgen-7b — XGen-7B
- https://tensor.news/models/yi-6b — Yi 6B
- https://tensor.news/models/yi-34b — Yi-34B
- https://tensor.news/models/yi-9b — Yi-9B
- https://tensor.news/models/baichuan-2-7b — Baichuan 2-7B
- https://tensor.news/models/claude-opus-4-1 — Claude Opus 4.1
- https://tensor.news/models/chatglm2-6b — chatglm2-6b
- https://tensor.news/models/gpt-oss-120b — gpt-oss-120b
- https://tensor.news/models/internlm-20b — internlm-20b
- https://tensor.news/models/internlm-7b — internlm-7b
- https://tensor.news/models/o1 — o1
- https://tensor.news/models/o1-mini — o1-mini
- https://tensor.news/models/o1-preview — o1-preview
- https://tensor.news/models/o3 — o3
- https://tensor.news/models/o3-mini — o3-mini
- https://tensor.news/models/claude-opus-4-5 — Claude Opus 4.5
- https://tensor.news/models/o3-pro — o3-pro
- https://tensor.news/models/o4-mini — o4-mini
- https://tensor.news/models/open-llama-7b — open_llama_7b
- https://tensor.news/models/phi-3-medium-14b — phi-3-medium 14B
- https://tensor.news/models/phi-3-mini-3-8b — phi-3-mini 3.8B
- https://tensor.news/models/phi-3-small-7-4b — phi-3-small 7.4B
- https://tensor.news/models/stablelm-tuned-alpha-7b — stablelm-tuned-alpha-7b
- https://tensor.news/models/vicuna-13b-v1-1 — vicuna-13b-v1.1
- https://tensor.news/models/claude-opus-4-6 — Claude Opus 4.6
- https://tensor.news/models/claude-opus-4-7 — Claude Opus 4.7
- https://tensor.news/models/claude-opus-4-8 — Claude Opus 4.8
- https://tensor.news/models/claude-sonnet-4 — Claude Sonnet 4
- https://tensor.news/models/claude-sonnet-4-5 — Claude Sonnet 4.5
- https://tensor.news/models/claude-sonnet-4-6 — Claude Sonnet 4.6
- https://tensor.news/models/codeqwen1-5-7b — CodeQwen1.5-7B
- https://tensor.news/models/deepseek-coder-1-3b — DeepSeek Coder 1.3B
- https://tensor.news/models/baichuan1-7b — Baichuan1-7B
- https://tensor.news/models/deepseek-coder-33b — DeepSeek Coder 33B
- https://tensor.news/models/deepseek-coder-6-7b — DeepSeek Coder 6.7B
- https://tensor.news/models/deepseek-coder-v2-lite-base — DeepSeek-Coder-V2-Lite-Base
- https://tensor.news/models/deepseek-r1 — DeepSeek-R1
- https://tensor.news/models/deepseek-r1-may-2025 — DeepSeek-R1 (May 2025)
- https://tensor.news/models/deepseek-v2-moe-236b-may-2024 — DeepSeek-V2 (MoE-236B, May 2024)
- https://tensor.news/models/deepseek-v3 — DeepSeek-V3
- https://tensor.news/models/deepseek-v3-mar-2025 — DeepSeek-V3 (Mar 2025)
- https://tensor.news/models/deepseek-v3-1 — DeepSeek-V3.1
- https://tensor.news/models/deepseek-v3-2 — DeepSeek-V3.2
- https://tensor.news/models/baichuan2-13b — Baichuan2-13B
- https://tensor.news/models/deepseek-v3-2-exp — DeepSeek-V3.2-Exp
- https://tensor.news/models/deepseek-v4-pro — DeepSeek-V4-Pro
- https://tensor.news/models/dolly-2-0-12b — Dolly 2.0-12b
- https://tensor.news/models/falcon-2-11b — Falcon 2 11B
- https://tensor.news/models/falcon-180b — Falcon-180B
- https://tensor.news/models/falcon-40b — Falcon-40B
- https://tensor.news/models/falcon-7b — Falcon-7B
- https://tensor.news/models/glm-4-6 — GLM-4.6
- https://tensor.news/models/glm-4-7 — GLM-4.7
- https://tensor.news/models/glm-5 — GLM-5
- https://tensor.news/models/cerebras-gpt-13b — Cerebras-GPT-13B
- https://tensor.news/models/glm-5-1 — GLM-5.1
- https://tensor.news/models/glm-5-2 — GLM-5.2
- https://tensor.news/models/gpt-3-5-turbo-jan-2024 — GPT-3.5 Turbo (Jan 2024)
- https://tensor.news/models/gpt-3-5-turbo-jun-2023 — GPT-3.5 Turbo (Jun 2023)
- https://tensor.news/models/gpt-3-5-turbo-nov-2023 — GPT-3.5 Turbo (Nov 2023)
- https://tensor.news/models/gpt-4-jun-2023 — GPT-4 (Jun 2023)
- https://tensor.news/models/gpt-4-mar-2023 — GPT-4 (Mar 2023)
- https://tensor.news/models/gpt-4-turbo-apr-2024 — GPT-4 Turbo (Apr 2024)
- https://tensor.news/models/gpt-4-1 — GPT-4.1
- https://tensor.news/models/gpt-4-1-mini — GPT-4.1 mini
- https://tensor.news/models/gpt-4-1-nano — GPT-4.1 nano
- https://tensor.news/models/gpt-4-5 — GPT-4.5
- https://tensor.news/models/gpt-4o-aug-2024 — GPT-4o (Aug 2024)
- https://tensor.news/models/gpt-4o-may-2024 — GPT-4o (May 2024)
- https://tensor.news/models/gpt-4o-nov-2024 — GPT-4o (Nov 2024)
- https://tensor.news/models/gpt-4o-mini — GPT-4o mini
- https://tensor.news/models/gpt-5 — GPT-5
- https://tensor.news/models/gpt-5-pro — GPT-5 Pro
- https://tensor.news/models/claude-2 — Claude 2
- https://tensor.news/models/gpt-5-mini — GPT-5 mini
- https://tensor.news/models/gpt-5-nano — GPT-5 nano
- https://tensor.news/models/gpt-5-1 — GPT-5.1
- https://tensor.news/models/gpt-5-2 — GPT-5.2
- https://tensor.news/models/gpt-5-2-pro — GPT-5.2 Pro
- https://tensor.news/models/gpt-5-3-codex — GPT-5.3 Codex
- https://tensor.news/models/gpt-5-4 — GPT-5.4
- https://tensor.news/models/gpt-5-4-mini — GPT-5.4 Mini
- https://tensor.news/models/gpt-5-4-nano — GPT-5.4 Nano
- https://tensor.news/models/gpt-5-4-pro — GPT-5.4 Pro
- https://tensor.news/models/claude-2-1 — Claude 2.1
- https://tensor.news/models/gpt-5-5 — GPT-5.5
- https://tensor.news/models/gpt-5-5-pro — GPT-5.5 Pro
- https://tensor.news/models/gemini-1-0-pro — Gemini 1.0 Pro
- https://tensor.news/models/gemini-1-5-flash-may-2024 — Gemini 1.5 Flash (May 2024)
- https://tensor.news/models/gemini-1-5-flash-sep-2024 — Gemini 1.5 Flash (Sep 2024)
- https://tensor.news/models/gemini-1-5-pro-may-2024 — Gemini 1.5 Pro (May 2024)
- https://tensor.news/models/gemini-1-5-pro-sept-2024 — Gemini 1.5 Pro (Sept 2024)
- https://tensor.news/models/gemini-2-0-flash-dec-2024 — Gemini 2.0 Flash (Dec 2024)
- https://tensor.news/models/claude-3-haiku — Claude 3 Haiku
- https://tensor.news/models/gemini-2-0-flash-feb-2025 — Gemini 2.0 Flash (Feb 2025)
- https://tensor.news/models/gemini-2-0-flash-thinking-jan-2025 — Gemini 2.0 Flash Thinking (Jan 2025)
- https://tensor.news/models/gemini-2-0-pro — Gemini 2.0 Pro
- https://tensor.news/models/gemini-2-5-flash-apr-2025 — Gemini 2.5 Flash (Apr 2025)
- https://tensor.news/models/gemini-2-5-flash-jun-2025 — Gemini 2.5 Flash (Jun 2025)
- https://tensor.news/models/gemini-2-5-flash-may-2025 — Gemini 2.5 Flash (May 2025)
- https://tensor.news/models/gemini-2-5-flash-sep-2025 — Gemini 2.5 Flash (Sep 2025)
- https://tensor.news/models/gemini-2-5-pro-jun-2025 — Gemini 2.5 Pro (Jun 2025)
- https://tensor.news/models/gemini-2-5-pro-mar-2025 — Gemini 2.5 Pro (Mar 2025)
- https://tensor.news/models/gemini-2-5-pro-may-2025 — Gemini 2.5 Pro (May 2025)

### Benchmarks
- https://tensor.news/benchmarks/lech-mazur-writing — Lech Mazur Writing
- https://tensor.news/benchmarks/mmlu — MMLU
- https://tensor.news/benchmarks/the-agent-company — The Agent Company
- https://tensor.news/benchmarks/hle — HLE
- https://tensor.news/benchmarks/winogrande — Winogrande
- https://tensor.news/benchmarks/gpqa-diamond — GPQA diamond
- https://tensor.news/benchmarks/math-level-5 — MATH level 5
- https://tensor.news/benchmarks/otis-mock-aime-2024-2025 — OTIS Mock AIME 2024-2025
- https://tensor.news/benchmarks/weirdml — WeirdML
- https://tensor.news/benchmarks/cybench — Cybench
- https://tensor.news/benchmarks/simplebench — SimpleBench
- https://tensor.news/benchmarks/simpleqa-verified — SimpleQA Verified
- https://tensor.news/benchmarks/balrog — Balrog
- https://tensor.news/benchmarks/geobench — GeoBench
- https://tensor.news/benchmarks/vpct — VPCT
- https://tensor.news/benchmarks/gso-bench — GSO-Bench
- https://tensor.news/benchmarks/swe-bench-verified — SWE-Bench verified
- https://tensor.news/benchmarks/arc-agi — ARC-AGI
- https://tensor.news/benchmarks/arc-agi-2 — ARC-AGI-2
- https://tensor.news/benchmarks/frontiermath-tiers-1-3-v2-private — FrontierMath-Tiers-1-3-v2-Private
- https://tensor.news/benchmarks/frontiermath-tier-4-v2-private — FrontierMath-Tier-4-v2-Private
- https://tensor.news/benchmarks/chess-puzzles — Chess Puzzles
- https://tensor.news/benchmarks/apex-agents — APEX-Agents
- https://tensor.news/benchmarks/terminal-bench — Terminal Bench
- https://tensor.news/benchmarks/frontiermath-2025-02-28-private — FrontierMath-2025-02-28-Private
- https://tensor.news/benchmarks/critpt — CritPt
- https://tensor.news/benchmarks/frontiermath-tier-4-2025-07-01-private — FrontierMath-Tier-4-2025-07-01-Private
- https://tensor.news/benchmarks/remote-labor-index — Remote Labor Index
- https://tensor.news/benchmarks/gdpval — GDPval
- https://tensor.news/benchmarks/posttrainbench — PostTrainBench
- https://tensor.news/benchmarks/cl-bench — CL-bench
- https://tensor.news/benchmarks/deepresearch-bench — DeepResearch Bench
- https://tensor.news/benchmarks/gbaeval — GBAEval
- https://tensor.news/benchmarks/exploitbench — ExploitBench
- https://tensor.news/benchmarks/cl-bench-life — CL-bench Life
- https://tensor.news/benchmarks/cursorbench — CursorBench
- https://tensor.news/benchmarks/piqa — PIQA
- https://tensor.news/benchmarks/gsm8k — GSM8K
- https://tensor.news/benchmarks/triviaqa — TriviaQA
- https://tensor.news/benchmarks/arc-ai2 — ARC AI2
- https://tensor.news/benchmarks/bbh — BBH
- https://tensor.news/benchmarks/hellaswag — HellaSwag
- https://tensor.news/benchmarks/aider-polyglot — Aider polyglot
- https://tensor.news/benchmarks/fiction-livebench — Fiction.LiveBench
- https://tensor.news/benchmarks/openbookqa — OpenBookQA
- https://tensor.news/benchmarks/anli — ANLI
- https://tensor.news/benchmarks/cadeval — CadEval
- https://tensor.news/benchmarks/osworld — OSWorld
- https://tensor.news/benchmarks/osworld-2-0 — OSWorld 2.0
- https://tensor.news/benchmarks/scienceqa — ScienceQA
- https://tensor.news/benchmarks/lambada — LAMBADA

### Labs
- https://tensor.news/labs/qwen — Qwen
- https://tensor.news/labs/meta-ai — Meta AI
- https://tensor.news/labs/openai — OpenAI
- https://tensor.news/labs/deepseek — DeepSeek
- https://tensor.news/labs/nvidia — NVIDIA
- https://tensor.news/labs/google-deepmind — Google DeepMind
- https://tensor.news/labs/eleutherai — EleutherAI
- https://tensor.news/labs/zhipu-ai — Zhipu AI
- https://tensor.news/labs/hugging-face — Hugging Face
- https://tensor.news/labs/ibm-research — IBM Research
- https://tensor.news/labs/red-hat-ai — Red Hat AI
- https://tensor.news/labs/apple — Apple
- https://tensor.news/labs/h2o-ai — H2O.ai
- https://tensor.news/labs/minimax — MiniMax
- https://tensor.news/labs/moonshot-ai — Moonshot AI
- https://tensor.news/labs/mistral-ai — Mistral AI
- https://tensor.news/labs/microsoft — Microsoft
- https://tensor.news/labs/tii — Technology Innovation Institute
- https://tensor.news/labs/nous-research — Nous Research

### Papers
- https://tensor.news/papers/w3138516171 — Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- https://tensor.news/papers/w2964015378 — Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
- https://tensor.news/papers/w4292779060 — Aion Framework: Dimensional Emergence of AI Consciousness, Observer-Induced Collapse, and Cosmological Portal Dynamics
- https://tensor.news/papers/w2970641574 — Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- https://tensor.news/papers/w2493916176 — Enriching Word Vectors with Subword Information
- https://tensor.news/papers/w4390874575 — Segment Anything
- https://tensor.news/papers/w3140854437 — Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
- https://tensor.news/papers/w2911489562 — BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- https://tensor.news/papers/w3177318507 — Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- https://tensor.news/papers/w3133702157 — On the Dangers of Stochastic Parrots
- https://tensor.news/papers/w4323655724 — ChatGPT for good? On opportunities and challenges of large language models for education
- https://tensor.news/papers/w4378212544 — Dictionary learning for integrative, multimodal and scalable single-cell analysis
- https://tensor.news/papers/w3168997536 — A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
- https://tensor.news/papers/w2664267452 — Artificial intelligence in healthcare: past, present and future
- https://tensor.news/papers/w4322718191 — LLaMA: Open and Efficient Foundation Language Models
- https://tensor.news/papers/w4360620450 — Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy
- https://tensor.news/papers/w3185341429 — Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
- https://tensor.news/papers/w4319662928 — Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models
- https://tensor.news/papers/w3170841864 — Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
- https://tensor.news/papers/w4384071683 — Large language models encode clinical knowledge
- https://tensor.news/papers/w4384918448 — Llama 2: Open Foundation and Fine-Tuned Chat Models
- https://tensor.news/papers/w4327810158 — GPT-4 Technical Report
- https://tensor.news/papers/w3095319910 — GPT-3: Its Nature, Scope, Limits, and Consequences
- https://tensor.news/papers/w2958089299 — A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
- https://tensor.news/papers/w4384464487 — Students’ voices on generative AI: perceptions, benefits, and challenges in higher education
- https://tensor.news/papers/w2970476646 — Language Models as Knowledge Bases?
- https://tensor.news/papers/w4317910584 — ChatGPT: Bullshit spewer or the end of traditional assessments in higher education?
- https://tensor.news/papers/w4321499901 — What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education
- https://tensor.news/papers/w4365143687 — Foundation models for generalist medical artificial intelligence
- https://tensor.news/papers/w4360836968 — Sparks of Artificial General Intelligence: Early experiments with GPT-4
- https://tensor.news/papers/w4387835442 — Generative Agents: Interactive Simulacra of Human Behavior
- https://tensor.news/papers/w3177813494 — Evaluating Large Language Models Trained on Code
- https://tensor.news/papers/w2953356739 — ERNIE: Enhanced Language Representation with Informative Entities
- https://tensor.news/papers/w4362515116 — A Survey of Large Language Models
- https://tensor.news/papers/w4225323055 — Flamingo: a Visual Language Model for Few-Shot Learning
- https://tensor.news/papers/w3173777717 — Making Pre-trained Language Models Better Few-shot Learners
- https://tensor.news/papers/w4386693657 — Generative AI
- https://tensor.news/papers/w4368367885 — ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations
- https://tensor.news/papers/w4307079201 — Scaling Instruction-Finetuned Language Models
- https://tensor.news/papers/w4393065402 — A survey on large language model based autonomous agents
- https://tensor.news/papers/w4383312437 — A comprehensive AI policy education framework for university teaching and learning
- https://tensor.news/papers/w3098267758 — AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
- https://tensor.news/papers/w4323050332 — Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios
- https://tensor.news/papers/w4387321091 — Efficient Memory Management for Large Language Model Serving with PagedAttention
- https://tensor.news/papers/w4366208220 — DINOv2: Learning Robust Visual Features without Supervision
- https://tensor.news/papers/w4399083018 — Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation
- https://tensor.news/papers/w4389326242 — Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- https://tensor.news/papers/w3034723486 — Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
- https://tensor.news/papers/w4387500346 — The future landscape of large language models in medicine
- https://tensor.news/papers/w4391876619 — Lost in the Middle: How Language Models Use Long Contexts
- https://tensor.news/papers/w4385878593 — New Era of Artificial Intelligence in Education: Towards a Sustainable Multifaceted Revolution
- https://tensor.news/papers/w4383346782 — The imperative for regulatory oversight of large language models (or generative AI) in healthcare
- https://tensor.news/papers/w4322766882 — Parameter-efficient fine-tuning of large-scale pre-trained language models
- https://tensor.news/papers/w4381982883 — ChatGPT for Education and Research: Opportunities, Threats, and Strategies
- https://tensor.news/papers/w4376226279 — Multimodal Learning With Transformers: A Survey
- https://tensor.news/papers/w4366817968 — Generative AI at Work
- https://tensor.news/papers/w2997591391 — Unified Vision-Language Pre-Training for Image Captioning and VQA
- https://tensor.news/papers/w4312220150 — A large language model for electronic health records
- https://tensor.news/papers/w4389991792 — Autonomous chemical research with large language models

### Compare
- https://tensor.news/compare/claude-fable-5-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/gpt-5-5-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/gemini-3-1-pro-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/ibm-research-powermoe-3b-vs-llama-3-1-405b
- https://tensor.news/compare/ibm-research-powermoe-3b-vs-phi-3-small-7-4b
- https://tensor.news/compare/deepseek-v3-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/glm-5-2-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/ibm-research-powermoe-3b-vs-kimi-k2-sep-2025
- https://tensor.news/compare/falcon-180b-vs-ibm-research-powermoe-3b
- https://tensor.news/compare/claude-fable-5-vs-gpt-5-5
- https://tensor.news/compare/claude-fable-5-vs-gemini-3-1-pro
- https://tensor.news/compare/claude-fable-5-vs-llama-3-1-405b
- https://tensor.news/compare/claude-fable-5-vs-phi-3-small-7-4b
- https://tensor.news/compare/claude-fable-5-vs-deepseek-v3
- https://tensor.news/compare/claude-fable-5-vs-glm-5-2
- https://tensor.news/compare/claude-fable-5-vs-kimi-k2-sep-2025
- https://tensor.news/compare/claude-fable-5-vs-falcon-180b
- https://tensor.news/compare/gemini-3-1-pro-vs-gpt-5-5
- https://tensor.news/compare/gpt-5-5-vs-llama-3-1-405b
- https://tensor.news/compare/gpt-5-5-vs-phi-3-small-7-4b
- https://tensor.news/compare/deepseek-v3-vs-gpt-5-5
- https://tensor.news/compare/glm-5-2-vs-gpt-5-5
- https://tensor.news/compare/gpt-5-5-vs-kimi-k2-sep-2025
- https://tensor.news/compare/falcon-180b-vs-gpt-5-5
- https://tensor.news/compare/gemini-3-1-pro-vs-llama-3-1-405b
- https://tensor.news/compare/gemini-3-1-pro-vs-phi-3-small-7-4b
- https://tensor.news/compare/deepseek-v3-vs-gemini-3-1-pro
- https://tensor.news/compare/gemini-3-1-pro-vs-glm-5-2
- https://tensor.news/compare/gemini-3-1-pro-vs-kimi-k2-sep-2025
- https://tensor.news/compare/falcon-180b-vs-gemini-3-1-pro
- https://tensor.news/compare/llama-3-1-405b-vs-phi-3-small-7-4b
- https://tensor.news/compare/deepseek-v3-vs-llama-3-1-405b
- https://tensor.news/compare/glm-5-2-vs-llama-3-1-405b
- https://tensor.news/compare/kimi-k2-sep-2025-vs-llama-3-1-405b
- https://tensor.news/compare/falcon-180b-vs-llama-3-1-405b
- https://tensor.news/compare/deepseek-v3-vs-phi-3-small-7-4b
- https://tensor.news/compare/glm-5-2-vs-phi-3-small-7-4b
- https://tensor.news/compare/kimi-k2-sep-2025-vs-phi-3-small-7-4b
- https://tensor.news/compare/falcon-180b-vs-phi-3-small-7-4b
- https://tensor.news/compare/deepseek-v3-vs-glm-5-2
- https://tensor.news/compare/deepseek-v3-vs-kimi-k2-sep-2025
- https://tensor.news/compare/deepseek-v3-vs-falcon-180b
- https://tensor.news/compare/glm-5-2-vs-kimi-k2-sep-2025
- https://tensor.news/compare/falcon-180b-vs-glm-5-2
- https://tensor.news/compare/falcon-180b-vs-kimi-k2-sep-2025