Google: palm
1 benchmarks
Leaderboard position
#535
Overall rank (of 1121 models)
1022
Elo rating
1
Benchmarks
Top 47.7%
Percentile
In Google (of 72 models)
Above: SpaceXAI: Grok 3 Reasoning Beta #534
Below: surogate: rune-26b-a4b-v3 #536
Benchmark highlights
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 | ~89.29 | 50% | — |
| AIME 2025 | ~71.6 | 50% | — |
| AIME 2026 | ~76.74 | 50% | — |
| HMMT Feb 2026 | ~68.26 | 50% | — |
| GPQA Diamond | ~61.77 | 50% | — |
| MMLU-Pro | ~65.33 | 50% | — |
| Humanity's Last Exam (no tools) | ~14.62 | 50% | — |
| IFEval | ~84.57 | 50% | — |
| IFBench | ~56.11 | 50% | — |
| HumanEval | ~78.58 | 50% | — |
| MBPP | ~83.41 | 50% | — |
| Terminal-Bench v2.1 | ~27.31 | 50% | — |
| MMLU | ~71.99 | 50% | — |
| SWE-bench Verified | ~44.45 | 50% | — |
| SWE-bench Pro | ~23.04 | 50% | — |
| SciCode | ~29.54 | 50% | — |
| AA-LCR | ~46.37 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~19.84 | 50% | — |
| GSM8K | ~89.12 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~59.76 | 50% | — |
| MMMU-Pro | ~56.1 | 50% | — |
| MATH | ~67.79 | 50% | — |
| BBH | ~69.05 | 50% | — |