Z.ai: cogagent
1 benchmarks
Leaderboard position
#1055
Overall rank (of 1121 models)
-365
Elo rating
1
Benchmarks
Top 94.1%
Percentile
In Z.ai (of 18 models)
Above: Show Lab: showui-2b #1054
Below: Technology Innovation Institute: Falcon H1 Tiny 90M Instruct #1056
Benchmark highlights
Best benchmark
ScreenSpot-Pro
7.7
Worst benchmark
ScreenSpot-Pro
7.7
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| MATH-500 | ~65.23 | 50% | — |
| AIME 2025 | ~26.09 | 50% | — |
| AIME 2026 | ~49.91 | 50% | — |
| HMMT Feb 2026 | ~41.33 | 50% | — |
| GPQA Diamond | ~31.25 | 50% | — |
| MMLU-Pro | ~31.3 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~65.61 | 50% | — |
| IFBench | ~33.15 | 50% | — |
| HumanEval | ~38.3 | 50% | — |
| MBPP | ~30.66 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~36.25 | 50% | — |
| SWE-bench Verified | ~0.94 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~7.87 | 50% | — |
| AA-LCR | ~19.27 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~36.96 | 50% | — |
| -(CoderPPL) | ~-8.47 | 50% | — |
| LiveCodeBench v6 | ~28.07 | 50% | — |
| MMMU-Pro | ~30.06 | 50% | — |
| MATH | ~9.58 | 50% | — |
| BBH | ~38.27 | 50% | — |