Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Gemini 2.5 Pro9 results · 9 benchmarks
Model card

Gemini 2.5 Pro.

unknown1 current SOTA
§ 02 · Benchmarks

Every benchmark Gemini 2.5 Pro has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SimpleQANatural Language Processing · Question Answeringaccuracy54.0%#1/7source ↗
02MMMUMultimodal · Image-Text-to-Textaccuracy82.0%#5/36source ↗
03Video-MMEMultimodal · Video Understandingaccuracy84.3%#5/24source ↗
04MMMUMultimodal · Visual Question Answeringaccuracy82.0%#8/30source ↗
05AIME 2025Reasoning · Mathematical Reasoningaccuracy88.0%#11/22source ↗
06LiveCodeBenchComputer Code · Code Generationpass-174.2%#13/24source ↗
07GPQA DiamondReasoning · Multi-step Reasoningaccuracy86.4%#14/74source ↗
08HLEReasoning · Multi-step Reasoningaccuracy21.6%#19/36source ↗
09SWE-Bench VerifiedComputer Code · Code Generationaccuracy59.6%#20/22source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Gemini 2.5 Pro actually performs.

Natural Language Processing
1
benchmark
avg rank #1.0 · 1 SOTA
Multimodal
3
benchmarks
avg rank #6.0
Reasoning
3
benchmarks
avg rank #14.7
Computer Code
2
benchmarks
avg rank #16.5
§ 04 · Papers

1 paper with results for Gemini 2.5 Pro.

  1. 2025-07-07· 9 results

    Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
9
results
0 of 9 rows marked verified.