Z.AI
availableShows if the model has enough results for an index.GLM-4.6
GLM-4.6 is a reasoning model from Z.AI. 19 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.42.2 ±5.2
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.79/s
Input / 1MUS dollars per 1M input tokens.$0.43
Output / 1MUS dollars per 1M output tokens.$1.75
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1440 (#66)
50 is the middle of the board. The range shows the doubt in the index.
35,061 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
19 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. |
|---|---|---|---|---|---|---|
| AIME | Math | 92.7% | 56.9 | — | 16 Apr 2026 | Vals AI |
| MGSM | Multilingual | 89.7% | — | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 82.2% | 50.0 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 81.0% | 58.0 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 76.9% | 54.0 | — | — | Victor Barres et al. |
| GPQA Diamond | Knowledge | 74.5% | 47.0 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 63.2% | 33.3 | — | — | Artificial Analysis |
| SWE-bench Verified | Coding | 61.8% | 47.1 | mini-SWE-agent | 1 Sept 2026 | SWE-bench team |
| SWE-bench Verified | Coding | 55.4% | 42.0 | mini-SWE-agent | 26 Feb 2026 | SWE-bench team |
| Terminal-Bench 1.0 | Agentic | 42.5% | 47.6 | — | 12 Jan 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 36.7% | 26.4 | — | — | Artificial Analysis |
| Terminal-Bench 2.0 | Agentic | 28.1% | 42.7 | — | 4 Jun 2026 | Vals AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 26.3% | 26.5 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 21.4% | 40.3 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 14.9% | 41.1 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 5.5% | 30.5 | — | — | Artificial Analysis |
| IOI v1 | Coding | 4.3% | 42.4 | — | 9 Aug 2026 | Vals AI |
| FrontierMath-2025-02-28-Private | Math | 3.8% | 34.2 | — | — | Epoch AI |
| Vibe Code Bench v1.1 | Coding | 3.1% | 43.5 | OpenHands | 21 Sept 2026 | Vals AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 2.1% | 45.8 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
19 benchmarks count, from 20 of 21 results. A grey row does not count. Too few models took that benchmark.