Z.AI
availableShows if the model has enough results for an index.GLM-5.1
GLM-5.1 is a reasoning model from Z.AI in the GLM-5 family. 39 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.57.8 ±4.1
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.18/s
Input / 1MUS dollars per 1M input tokens.$0.966
Output / 1MUS dollars per 1M output tokens.$3.04
ContextMaximum tokens in one request.205K
EloLMArena rating and rank.1462 (#33)
50 is the middle of the board. The range shows the doubt in the index.
48,901 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
39 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 | 97.7% | 68.9 | — | — | Victor Barres et al. |
| AIME 2026 | Math | 95.3% | 54.4 | — | — | Qwen |
| Harvard-MIT Mathematics Tournament November 2025 | Math | 94.0% | — | — | — | Qwen |
| OTIS Mock AIME 2024-2025 | Math | 93.3% | 63.7 | — | — | Epoch AI |
| AIME | Math | 91.9% | 56.6 | — | 16 Apr 2026 | Vals AI |
| GPQA diamond | Knowledge | 89.9% | 61.2 | — | — | Epoch AI |
| MMLU Pro | Knowledge | 86.9% | 57.5 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 86.8% | 57.5 | — | — | Artificial Analysis |
| GPQA Diamond | Knowledge | 86.2% | 57.8 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 84.5% | 56.3 | — | 1 Sept 2026 | Vals AI |
| MMAnswerBench | Math | 83.8% | — | — | — | Qwen |
| Harvard-MIT Mathematics Tournament February 2026 | Math | 82.6% | 51.9 | — | — | Qwen |
| LiveCodeBench | Coding | 81.4% | 58.3 | — | 1 Sept 2026 | Vals AI |
| SWE-bench | Coding | 76.4% | 58.8 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 76.3% | 66.5 | — | — | Artificial Analysis |
| SWE-Bench verified | Coding | 74.2% | 57.0 | — | — | Epoch AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 73.7% | 59.2 | — | — | Artificial Analysis |
| MCP Atlas | Agentic | 71.8% | 62.2 | — | — | OpenAI |
| τ³-Bench Tool-Agent-User Evaluation | Agentic | 70.6% | 55.2 | — | — | Sierra Research |
| CyberGym | Agentic | 68.7% | 63.2 | — | — | Zhun Wang et al. |
| BrowseComp | Agentic | 68.0% | 57.0 | — | — | OpenAI |
| SWE-Rebench | Coding | 62.7% | — | — | — | Nebius |
| Claw-Eval | Agentic | 62.3% | 56.3 | — | — | Bowen Ye et al. |
| Gert Labs Composite Game Benchmark | Agentic | 60.1% | 65.8 | — | — | Gert Labs |
| SWE-bench Pro | Coding | 58.4% | 60.5 | — | — | Xiang Deng et al. |
| Terminal-Bench 2.1 | Agentic | 56.9% | 57.6 | — | 21 Sept 2026 | Vals AI |
| Artificial Analysis Coding Index | Coding | 55.8% | 58.3 | — | — | Artificial Analysis |
| Terminal-Bench 2.0 | Agentic | 53.9% | 61.2 | — | 4 Jun 2026 | Vals AI |
| OpenHarmony Bench v1.0 | Coding | 52.3% | 61.1 | — | — | OpenHarmony Bench authors |
| Humanity's Last Exam | Knowledge | 52.3% | 73.1 | — | — | Center for AI Safety et al. |
| Artificial Analysis SciCode | Coding | 44.8% | 55.0 | — | — | Artificial Analysis |
| NL2Repo | Coding | 42.7% | 58.4 | — | — | MiniMax |
| SimpleQA Verified | Knowledge | 34.0% | 53.0 | — | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 33.4% | 61.8 | — | — | Epoch AI |
| Vibe Code Bench v1.1 | Coding | 31.5% | 55.3 | OpenHands | 21 Sept 2026 | Vals AI |
| GDPval-AA normalized | Agentic | 30.2% | 58.8 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 30.1% | 57.2 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 26.1% | 55.0 | — | — | Artificial Analysis |
| Code Migration | Coding | 25.8% | 61.4 | — | 21 Sept 2026 | Vals AI |
| Artificial Analysis Agentic Index | Agentic | 25.2% | 57.7 | — | — | Artificial Analysis |
| FrontierMath-Tiers-1-3-v2-Private | Math | 24.9% | 45.5 | none effort | — | Epoch AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 23.7% | 43.2 | — | — | Artificial Analysis |
| Chess Puzzles | Reasoning | 19.0% | 48.1 | — | — | Epoch AI |
| ResearchClawBench | Agentic | 18.2% | — | — | — | InternScience |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 12.5% | 57.0 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 4.6% | 48.0 | — | — | Artificial Analysis |
| ProgramBench | Coding | 0.0% | — | — | 21 Sept 2026 | Vals AI |
39 benchmarks count, from 42 of 47 results. A grey row does not count. Too few models took that benchmark.