Z.AI
availableShows if the model has enough results for an index.GLM-4.7
GLM-4.7 is a reasoning model from Z.AI. 28 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.50.2 ±4.6
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.24/s
Input / 1MUS dollars per 1M input tokens.$0.4
Output / 1MUS dollars per 1M output tokens.$1.75
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1436 (#78)
50 is the middle of the board. The range shows the doubt in the index.
11,893 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
28 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 95.9% | 67.6 | — | — | Victor Barres et al. |
| American Invitational Mathematics Examination 2025 | Math | 95.7% | 51.9 | — | — | Mathematical Association of America |
| AIME | Math | 93.3% | 57.2 | — | 16 Apr 2026 | Vals AI |
| Artificial Analysis LiveCodeBench | Coding | 89.4% | — | — | — | Artificial Analysis |
| MGSM | Multilingual | 88.2% | — | — | 9 Jan 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 85.9% | 56.6 | — | — | Artificial Analysis |
| Graduate-Level Google-Proof Q&A | Knowledge | 85.7% | 57.4 | — | — | David Rein et al. |
| LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code | Coding | 84.9% | 61.5 | — | — | Naman Jain et al. |
| Massive Multitask Language Understanding Professional | Knowledge | 84.3% | 53.3 | — | — | Yubo Wang et al. |
| GPQA diamond | Knowledge | 83.3% | 55.2 | — | — | Epoch AI |
| OTIS Mock AIME 2024-2025 | Math | 83.3% | 58.1 | — | — | Epoch AI |
| MMLU Pro | Knowledge | 82.7% | 50.9 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 82.2% | 59.1 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 80.0% | 52.1 | — | 1 Sept 2026 | Vals AI |
| Software Engineering Benchmark Verified | Coding | 73.8% | 56.7 | — | — | Carlos E. Jimenez et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 71.0% | 57.4 | — | — | Artificial Analysis |
| SWE-bench | Coding | 69.4% | 53.2 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 67.9% | 58.0 | — | — | Artificial Analysis |
| SWE-Rebench | Coding | 58.7% | — | — | — | Nebius |
| BrowseComp | Agentic | 52.0% | 43.6 | — | — | OpenAI |
| Terminal-Bench 1.0 | Agentic | 50.0% | 53.9 | — | 12 Jan 2026 | Vals AI |
| Artificial Analysis Coding Index | Coding | 45.3% | 50.9 | — | — | Artificial Analysis |
| Gert Labs Composite Game Benchmark | Agentic | 40.0% | 48.0 | — | — | Gert Labs |
| Terminal-Bench 2.0 | Agentic | 38.2% | 49.9 | — | 4 Jun 2026 | Vals AI |
| SimpleQA Verified | Knowledge | 32.2% | 51.4 | — | — | Epoch AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 29.3% | 50.1 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 27.4% | 54.3 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 25.0% | 54.8 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 24.8% | 49.8 | — | — | Center for AI Safety et al. |
| Artificial Analysis Intelligence Index | Knowledge | 22.2% | 50.2 | — | — | Artificial Analysis |
| VITA-Bench | Agentic | 15.5% | 35.8 | — | — | Meituan LongCat Team |
| IOI v1 | Coding | 7.6% | 44.2 | — | 9 Aug 2026 | Vals AI |
| Chess Puzzles | Reasoning | 6.0% | 31.3 | — | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 2.4% | 32.9 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 1.7% | 41.9 | — | — | Artificial Analysis |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 0.0% | 43.4 | — | — | Epoch AI |
28 benchmarks count, from 33 of 36 results. A grey row does not count. Too few models took that benchmark.