GLM-5.3-Flash
- Best result
- 93.88onOTIS Mock AIME 2024-2025unverified
- Standing
- #53 of 170 on OTIS Mock AIME 2024-2025 — upper half of the field
- Leads
- 0 of 14 benchmarks
- Evidence
- 0 of 14 scores independently reproduced
- third-party
- unverified
Each bar is drawn on its own benchmark's scale — the ceiling that benchmark states where it has one (of 100), otherwise the best score recorded on it (rel. 2103). A benchmark that states neither draws no bar.
| Benchmark | Score | Evidence status | Released |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.88accuracy (%) | unverifiedT2 | 2026-08-20 |
| ARC-AGI | 91accuracy (%) | third-partyT1 | 2026-08-20https://arcprize.org/leaderboard |
| GPQA diamond | 90.49accuracy (%) | unverifiedT2 | 2026-08-20 |
| ARC-AGI-2 | 65.83accuracy (%) | unverifiedT2 | 2026-08-20 |
| FrontierMath-Tiers-1-3-v2-Private | 58.73accuracy (%) | unverifiedT2 | 2026-08-20 |
| APEX-Agents | 52.8accuracy (%) | unverifiedT2 | 2026-08-20 |
| Surface Evolver Bench | 52.5accuracy (%) | third-partyT1 | 2026-08-20https://yhenon.github.io/surface-evolver-llm-eval/ |
| PostTrainBench | 36.79accuracy (%) | unverifiedT2 | 2026-08-20 |
| FrontierCode | 31.83accuracy (%) | third-partyT1 | 2026-08-20https://cognition.com/frontiercode |
| ProofBench | 21accuracy (%) | third-partyT1 | 2026-08-20https://www.vals.ai/benchmarks/proof_bench |
| FrontierSWE | 18.13accuracy (%) | third-partyT1 | 2026-08-20https://www.frontierswe.com/ |
| FrontierMath-Tier-4-v2-Private | 17.07accuracy (%) | unverifiedT2 | 2026-08-20 |
| Chess Puzzles | 16.88accuracy (%) | unverifiedT2 | 2026-08-20 |
| Mystery Game Puzzles | 0accuracy (%) | unverifiedT2 | 2026-08-20 |
Claims drawn from cited facts, not live model generation.
Developed by Zhipu AI and released in 2026, this model is characterized by its origin and vintage rather than by an offered parameter scale.
2 cited facts
This model is scored on 14 tracked benchmarks. It holds no current top score on any of them. Its record is unverified, meaning no outside evaluation has either confirmed or disputed the reported results.
3 cited facts
On average, it trails the leader by 40.09 points under the disclosed harness—a wide gap that reads as well behind the front of the pack, not a capability claim. It holds the top score on 0 benchmarks, so it shows no genuine category leadership yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
GLM-5.3-Flash is an AI model developed by Zhipu AI, released 2026-08-20. Its benchmark record below tags every score as independently reproduced, third-party, self-reported, or unverified.
GLM-5.3-Flash has recorded scores on 14 benchmarks, each shown with its evidence status.
GLM-5.3-Flash has recorded scores on 14 benchmarks — ARC-AGI-2, ProofBench, GPQA diamond, OTIS Mock AIME 2024-2025, Chess Puzzles, FrontierMath-Tiers-1-3-v2-Private, and 8 more. The full table above shows each score with its evidence status.
0 of 14 tracked claims (0%) are independently reproduced; the rest are third-party, self-reported, unverified, or contradicted by an independent measurement.
GLM-5.3-Flash has 14 tracked claims: 9 unverified.
Plain text
tensor.news. "GLM-5.3-Flash — benchmark record". Benchmark record with evidence status for every score Updated 2026-11-18. https://tensor.news/models/glm-5-3-flash
BibTeX
@misc{tensornews_model_glm-5-3-flash-benchmark-record,
title = {{GLM-5.3-Flash — benchmark record}},
author = {{tensor.news}},
year = {2026},
month = {11},
howpublished = {\url{https://tensor.news/models/glm-5-3-flash}},
note = {Benchmark record with evidence status for every score},
urldate = {2026-11-18},
}