Google: veo-3
1 benchmarks
Leaderboard position
#671
Overall rank (of 1121 models)
732
Elo rating
1
Benchmarks
Top 59.9%
Percentile
In Google (of 72 models)
Above: OpenBMB: minicpm-v-4.6 #670
Below: Yandex: gpt-5-pro #672
Benchmark highlights
Best benchmark
Text-to-Video Arena (Arena.ai) (Sep 21, 2026)
1254
Worst benchmark
Text-to-Video Arena (Arena.ai) (Sep 21, 2026)
1254
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 | ~84.26 | 50% | — |
| AIME 2025 | ~62.09 | 50% | — |
| AIME 2026 | ~71.13 | 50% | — |
| HMMT Feb 2026 | ~62.63 | 50% | — |
| GPQA Diamond | ~55.39 | 50% | — |
| MMLU-Pro | ~58.22 | 50% | — |
| Humanity's Last Exam (no tools) | ~9.46 | 50% | — |
| IFEval | ~80.6 | 50% | — |
| IFBench | ~51.31 | 50% | — |
| HumanEval | ~70.15 | 50% | — |
| MBPP | ~72.38 | 50% | — |
| Terminal-Bench v2.1 | ~17.26 | 50% | — |
| MMLU | ~64.52 | 50% | — |
| SWE-bench Verified | ~35.35 | 50% | — |
| SWE-bench Pro | ~14.55 | 50% | — |
| SciCode | ~25.01 | 50% | — |
| AA-LCR | ~40.71 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~12.94 | 50% | — |
| GSM8K | ~78.22 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~53.13 | 50% | — |
| MMMU-Pro | ~50.65 | 50% | — |
| MATH | ~55.62 | 50% | — |
| BBH | ~62.61 | 50% | — |