Google · model passport
Palm 2
palm-2- Cloud only
- Proprietary licence
- Released 2023-05-10(curated)
- Overall · LMArena
- 1,139#365 of 396
- Best percentile
- 9.1Instruction following
- Cohort standing
- 26.1median 25.2
What the data says
Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 6.4 pct — Coding (1,153)
- 8.1 pct — Overall (1,139)
- 8.8 pct — Hard prompts (1,147)
Uneven: 2.7 percentile points between its best and worst axis — 9.1 pct on Instruction following versus 6.4 pct on Coding.
- Instruction following9.1 pct1,118Verify →
- Hard prompts8.8 pct1,147Verify →
- Overall8.1 pct1,139Verify →
- Coding6.4 pct1,153Verify →
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
palm-2 stands at 26.1 (raw mean 8.1) — measured on 4 of 27 axes.
palm-2 stands at 26.1 versus a cohort median of 25.2 across 38 models released within 180 days — above the peer median.
palm-2 scores at percentile 6.4 on Coding.
palm-2 scores at percentile 8.1 on Overall.
palm-2 ranks between #380 and #801 across 5 built-in weightings — best under "Conversation-first", worst under "All sources".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →