infly: infinity-parser2-flash
1 benchmarks
Leaderboard position
#97
Overall rank (of 1121 models)
2272
Elo rating
1
Benchmarks
Top 8.7%
Percentile
In infly (of 3 models)
Above: OpenAI: gpt-5.3-codex #96
Below: nanbeige: nanbeige4.3-33b #98
Benchmark highlights
Best benchmark
ParseBench
73.25
Worst benchmark
ParseBench
73.25
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 | ~99.2 | 50% | — |
| HMMT Feb 2026 | ~92.53 | 50% | — |
| GPQA Diamond | ~89.27 | 50% | — |
| MMLU-Pro | ~90.53 | 50% | — |
| Humanity's Last Exam (no tools) | ~36.86 | 50% | — |
| IFEval | ~96.75 | 50% | — |
| IFBench | ~76.8 | 50% | — |
| HumanEval | ~95.9 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~70.64 | 50% | — |
| MMLU | ~92.5 | 50% | — |
| SWE-bench Verified | ~83.67 | 50% | — |
| SWE-bench Pro | ~59.61 | 50% | — |
| SciCode | ~49.07 | 50% | — |
| AA-LCR | ~70.79 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~23.42 | 50% | — |
| Humanity's Last Exam (with tools) | ~49.54 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~88.31 | 50% | — |
| MMMU-Pro | ~79.57 | 50% | — |
| MATH | ~97.9 | 50% | — |
| BBH | ~88.4 | 50% | — |