Zhipu AI·released 2025-12-221 source
GLM-4.7 benchmark scores: 11 benchmarks tracked. 36% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 11 benchmarks·best result 83.32 on OTIS Mock AIME 2024-2025 (reproduced)·4 of 11 independently reproduced·$0.6/$2.2 per M tokens
Consensus: LiteLLM · Cross-check: models.dev, OpenRouter · See every model’s pricing →
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.32accuracy (%) | reproduced· optimizedT1 | 2025-12-22Epoch AI |
| GPQA diamond | 77.78accuracy (%) | reproduced· optimizedT1 | 2025-12-22Epoch AI |
| SimpleBench | 37.24accuracy (%) | unverifiedT1 | 2025-12-22SimpleBench Leaderboard |
| Terminal Bench | 33.39accuracy (%) | unverifiedT1 | 2025-12-22https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| SimpleQA Verified | 32.2accuracy (%) | unverifiedT2 | 2025-12-22 |
| Chess Puzzles | 16.88accuracy (%) | unverifiedT2 | 2025-12-22 |
| CL-bench | 15.9accuracy (%) | unverifiedT2 | 2025-12-22 |
| CL-bench Life | 10.9accuracy (%) | unverifiedT2 | 2025-12-22 |
| ProofBench | 6accuracy (%) | unverifiedT1 | 2025-12-22https://www.vals.ai/benchmarks/proof_bench |
| FrontierMath-2025-02-28-Private | 4.28accuracy (%) | reproduced· optimizedT1 | 2025-12-22Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | 0accuracy (%) | reproducedT1 | 2025-12-22Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by Zhipu AI and released in 2025.
2 cited facts
This model has scores on 11 tracked benchmarks and currently leads 0 of them. The record’s evidence status is independently reproduced.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 39.88 points.
1 cited fact
6 facts cross-checked across data sources: 1 corroborated, 1 single-source, 4 disputed.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, litellm_prices, modelsdev_models, openrouter_models
GLM-4.7 is an AI model developed by Zhipu AI, released 2025-12-22. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GLM-4.7 has recorded scores on 11 benchmarks, each shown with its evidence status.
GLM-4.7 has recorded scores on 11 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, SimpleQA Verified, Chess Puzzles, SimpleBench, FrontierMath-2025-02-28-Private, and 5 more. The full table above shows each score with its evidence status.
4 of 11 recorded scores (36%) are independently reproduced rather than self-reported by the lab.
GLM-4.7 has 11 tracked claims: 4 independently reproduced, 7 unverified.
Listed API pricing: $0.6 per million input tokens, $2.2 per million output tokens (prices disputed across sources). See the pricing block for the full breakdown.