Updated daily at 05:00 UTC
Vision-language
Gemini 2.5 Pro
- Released
- 25 Mar 2025
- Status
- Legacy
- Context
- 1M
- Max output
- 65.5K
- Input per 1M tokens
- $1.25
- Output per 1M tokens
- $10.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Jan 2025
- Reasoning
- Yes
- Modalities
- text, image, video, audio, pdf → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 37.2 | 40 | 3 of 4 |
| Coding & software engineering | 43.5 | Not ranked | 2 of 5 |
| Agentic tool use | 43.1 | 6 | 2 of 2 |
| Professional knowledge work | 30.3 | 5 | 1 of 1 |
| Vision & multimodal understanding | 54.0 | 4 | 2 of 3 |
| Human preference | 41.8 | 42 | 4 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 20.0% | Independent | — | 8 Dec 2025 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 82.4% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.3477 | Third party | — | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| SimpleBench | Score (AVG@5) | 62.4% | Third party | — | — | https://lmcouncil.ai/benchmarks via Epoch AI |
| SimpleBench | Score (AVG@5) | 51.6% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
| SimpleBench | Score (AVG@5) | 51.6% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 85.3% | Independent | — | 16 Nov 2025 | Epoch AI |
| GPQA Diamond | Accuracy | 84.8% | Independent | — | 5 Jun 2025 | Epoch AI |
| GPQA Diamond | Accuracy | 83.8% | Independent | — | 31 Mar 2025 | Epoch AI |
| GPQA Diamond | Accuracy | 66.7% | Independent | — | 3 Jun 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 0.0% | Independent | — | 11 Jun 2026 | Epoch AI |
| FrontierMath Tier 4 (v1) | Accuracy | 4.2% | Independent | — | 3 Jul 2025 | Epoch AI |
| FrontierMath Tier 4 (v1) | Accuracy | 2.1% | Independent | — | 3 Jul 2025 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 24.6% | Independent | — | 11 Jun 2026 | Epoch AI |
| FrontierMath Tiers 1-3 (v1) | Accuracy | 14.1% | Independent | — | 24 Nov 2025 | Epoch AI |
| FrontierMath Tiers 1-3 (v1) | Accuracy | 10.3% | Independent | — | 3 Jul 2025 | Epoch AI |
| MATH Level 5 | Accuracy | 95.9% | Independent | — | 8 May 2025 | Epoch AI |
| MATH Level 5 | Accuracy | 95.6% | Independent | — | 7 May 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 84.7% | Independent | — | 16 Nov 2025 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Aider Polyglot | Percent correct | 83.1% | Third party | 32K | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| Aider Polyglot | Percent correct | 79.1% | Third party | — | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| Aider Polyglot | Percent correct | 76.9% | Third party | — | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| Aider Polyglot | Percent correct | 72.9% | Third party | — | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| Aider Polyglot | Percent correct | 72.9% | Third party | — | — | Aider LLM Leaderboards via Epoch AI |
| CadEval | Overall pass rate | 64.0% | Third party | — | — | CadEval Dashboard via Epoch AI |
| GSO | OPT@1 | 3.9% | Third party | — | — | GSO Leaderboard via Epoch AI |
| GSO | OPT@1 | 3.9% | Third party | — | — | https://gso-bench.github.io/index.html via Epoch AI |
| METR Time Horizons | Average task success (Epoch's column) | 55.4% | Third party | — | — | METR - Measuring AI Ability to Complete Long Tasks via Epoch AI |
| SWE-bench Verified | % resolved | 57.6% | Independent | — | 13 Feb 2026 | Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 32.6% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 32.6% | Third party | — | — | Terminal-Bench v2 Leaderboard via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 26.1% | Third party | — | — | Terminal-Bench v2 Leaderboard via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 26.1% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 19.6% | Third party | — | — | Terminal-Bench v2 Leaderboard via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 19.6% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 16.4% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 16.4% | Third party | — | — | Terminal-Bench v2 Leaderboard via Epoch AI |
| WeirdML (v2) | Average accuracy | 54.0% | Third party | 16K | — | WeirdML Leaderboard via Epoch AI |
Agentic tool use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| BALROG | Average progress | 43.3% | Third party | — | — | https://balrogai.com/ via Epoch AI |
| Deep Research Bench (FutureSearch) | Average score | 42.8% | Third party | — | — | DeepResearchBench Leaderboard via Epoch AI |
| Deep Research Bench (FutureSearch) | Average score | 41.5% | Third party | — | — | https://evals.futuresearch.ai/#drb via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GDPval | Wins vs experts | 23.3% | Source not stated | — | — | Epoch AI via Epoch AI |
| TheAgentCompany | Tasks resolved | 30.3% | Third party | — | — | TheAgentCompany leaderboard via Epoch AI |
Long context
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 91.7% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 66.7% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 66.7% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 66.7% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GeoBench | Country accuracy | 86.0% | Third party | — | — | GeoBench leaderboard via Epoch AI |
| GeoBench | Country accuracy | 81.0% | Third party | — | — | GeoBench leaderboard via Epoch AI |
| GeoBench | Country accuracy | 81.0% | Third party | — | — | GeoBench leaderboard via Epoch AI |
| Visual Physics Comprehension Test (VPCT) | Correct | 48.0% | Third party | — | — | VPCT leaderboard via Epoch AI |
| Visual Physics Comprehension Test (VPCT) | Correct | 46.4% | Third party | — | — | VPCT leaderboard via Epoch AI |
| Visual Physics Comprehension Test (VPCT) | Correct | 40.5% | Third party | — | — | VPCT leaderboard via Epoch AI |
Writing
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 83.8% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 80.9% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 80.5% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1227 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 2731 | Independent | — | 25 Sep 2026 | Arena |
| Document Arena (arena.ai) | Arena score (Elo scale) | 1431 | Independent | — | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 25110 | Independent | — | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1446 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 124887 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1247 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 88831 | Independent | — | 28 Sep 2026 | Arena |
Other Gemini Pro versions
- Gemini 3.1 Pro19 Feb 2026
- Gemini 3 Pro18 Nov 2025
- Gemini 2.0 Pro6 Dec 2024
- Gemini 1.5 Pro15 Feb 2024
- Gemini 1.0 Pro Vision13 Dec 2023
- Gemini 1.0 Pro6 Dec 2023
Sources
- https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro
- https://ai.google.dev/gemini-api/docs/deprecations
- https://ai.google.dev/gemini-api/docs/changelog
- https://ai.google.dev/gemini-api/docs/pricing
- https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions
- https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-thinking-updates-march-2025/