typesafe: jev-1.14
1 benchmarks
Leaderboard position
#129
Overall rank (of 1121 models)
2111
Elo rating
1
Benchmarks
Top 11.5%
Percentile
In typesafe (of 2 models)
Above: Xiaomi: mimo-v2.6-flash #128
Below: Multiverse Computing: quasar-438b #130
Benchmark highlights
Best benchmark
When2Call
82
Worst benchmark
When2Call
82
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 | ~99.2 | 50% | — |
| AIME 2025 | ~100 | 50% | — |
| AIME 2026 | ~97.8 | 50% | — |
| HMMT Feb 2026 | ~89.4 | 50% | — |
| GPQA Diamond | ~85.73 | 50% | — |
| MMLU-Pro | ~90.53 | 50% | — |
| Humanity's Last Exam (no tools) | ~33.99 | 50% | — |
| IFEval | ~96.75 | 50% | — |
| IFBench | ~74.14 | 50% | — |
| HumanEval | ~95.9 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~65.06 | 50% | — |
| MMLU | ~92.5 | 50% | — |
| SWE-bench Verified | ~78.61 | 50% | — |
| SWE-bench Pro | ~54.9 | 50% | — |
| SciCode | ~46.55 | 50% | — |
| AA-LCR | ~67.65 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~18.47 | 50% | — |
| Humanity's Last Exam (with tools) | ~45.72 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~84.64 | 50% | — |
| MMMU-Pro | ~76.54 | 50% | — |
| MATH | ~97.9 | 50% | — |
| BBH | ~88.4 | 50% | — |