cloudflare: clef-omni
1 benchmarks
Leaderboard position
#738
Overall rank (of 1121 models)
596
Elo rating
1
Benchmarks
Top 65.8%
Percentile
In cloudflare (of 3 models)
Above: NVIDIA Corporation: NVIDIA Nemotron 3 Nano 4B #737
Below: Intern Language Models: internlm2_5-7b-chat #739
Benchmark highlights
Best benchmark
Decision Index v0.4.1
45
Worst benchmark
Decision Index v0.4.1
45
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 | ~81.9 | 50% | — |
| AIME 2025 | ~57.62 | 50% | — |
| AIME 2026 | ~68.5 | 50% | — |
| HMMT Feb 2026 | ~59.99 | 50% | — |
| GPQA Diamond | ~52.4 | 50% | — |
| MMLU-Pro | ~54.88 | 50% | — |
| Humanity's Last Exam (no tools) | ~7.04 | 50% | — |
| IFEval | ~78.74 | 50% | — |
| IFBench | ~49.06 | 50% | — |
| HumanEval | ~66.21 | 50% | — |
| MBPP | ~67.21 | 50% | — |
| Terminal-Bench v2.1 | ~12.55 | 50% | — |
| MMLU | ~61.01 | 50% | — |
| SWE-bench Verified | ~31.09 | 50% | — |
| SWE-bench Pro | ~10.57 | 50% | — |
| SciCode | ~22.89 | 50% | — |
| AA-LCR | ~38.05 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~73.1 | 50% | — |
| -(CoderPPL) | ~-2.52 | 50% | — |
| LiveCodeBench v6 | ~50.03 | 50% | — |
| MMMU-Pro | ~48.1 | 50% | — |
| MATH | ~49.91 | 50% | — |
| BBH | ~59.59 | 50% | — |