Amazon: amazon-transcribe
1 benchmarks
Leaderboard position
#760
Overall rank (of 1121 models)
549
Elo rating
1
Benchmarks
Top 67.8%
Percentile
In Amazon (of 8 models)
Above: Ai2: olmo-3.1-32b-think #759
Below: Lightricks: ltx-2.3 #761
Benchmark highlights
Best benchmark
-(Artificial Analysis Word Error Rate Index: AgentTalk)
-4.1
Worst benchmark
-(Artificial Analysis Word Error Rate Index: AgentTalk)
-4.1
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 | ~81.09 | 50% | — |
| AIME 2025 | ~56.08 | 50% | — |
| AIME 2026 | ~67.59 | 50% | — |
| HMMT Feb 2026 | ~59.08 | 50% | — |
| GPQA Diamond | ~51.36 | 50% | — |
| MMLU-Pro | ~53.73 | 50% | — |
| Humanity's Last Exam (no tools) | ~6.2 | 50% | — |
| IFEval | ~78.1 | 50% | — |
| IFBench | ~48.28 | 50% | — |
| HumanEval | ~64.84 | 50% | — |
| MBPP | ~65.42 | 50% | — |
| Terminal-Bench v2.1 | ~10.92 | 50% | — |
| MMLU | ~59.8 | 50% | — |
| SWE-bench Verified | ~29.61 | 50% | — |
| SWE-bench Pro | ~9.2 | 50% | — |
| SciCode | ~22.15 | 50% | — |
| AA-LCR | ~37.13 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~71.33 | 50% | — |
| -(CoderPPL) | ~-2.82 | 50% | — |
| LiveCodeBench v6 | ~48.95 | 50% | — |
| MMMU-Pro | ~47.22 | 50% | — |
| MATH | ~47.94 | 50% | — |
| BBH | ~58.55 | 50% | — |