Google DeepMind · model passport
gemini-2.5-flash-preview-04-17
gemini-2-5-flash-preview-04-17- Best percentile
- 82.1LiveBench
- Composite standing
- 55.1shrunk · 3/27 axes
What the data says
Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.
Uneven: 36.4 percentile points between its best and worst axis — 82.1 pct on LiveBench versus 45.7 pct on Humanity's Last Exam.
- LiveBench82.1 pct69.9%Verify →
- AIME (math)53 pct73.1%Verify →
- Humanity's Last Exam45.7 pct12.1%Verify →
- OverallNot benchmarked
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- SimpleBenchNot 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
- CodingNot benchmarked
- Instruction followingNot benchmarked
- Hard promptsNot 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.
gemini-2.5-flash-preview-04-17 stands at 55.1 (raw mean 60.3) — measured on 3 of 27 axes.
gemini-2.5-flash-preview-04-17 ranks between #215 and #273 across 2 built-in weightings — best under "Reasoning", 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 →