Model comparison
Claude Opus 4.1 vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.8 on the Noometry Index.
Last verified . 45 shared benchmarks.
GoogleSummary
- They share 45 benchmarks with published results for both. Claude Opus 4.1 scores higher in 4 categories and Gemini 2.5 Pro in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 2.5 Pro leads 44.5 to 26.2.
- The biggest single-benchmark swing is GDPval: 43.6% for Claude Opus 4.1 and 23.3% for Gemini 2.5 Pro.
- Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.1 | Gemini 2.5 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 44.9 |
| Released | 2025-08-05 | 2025-03-25 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 66K |
| Input $ / M tokens | $15 | $1.25 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 48 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.3 (#69), Gemini 2.5 Pro: 42.8 (#86)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| SWE-bench Verified | 73.3% | 57.6% |
| LMArena WebDev | 1390 | 1227 |
| WeirdML | 45.9% | 54% |
| LMArena Coding | 1479 | 1452 |
| ALE-Bench | 674.77 | 785.52 |
| AlgoTune | 1.34 | 1.51 |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| LiveBench Coding | — | 85.9% |
| CadEval | — | 64% |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 34.8 (#38), Gemini 2.5 Pro: 29.1 (#81)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | 38% | 32.6% |
| GDPval | 43.6% | 23.3% |
| DeepResearch Bench | 48.3% | 42.8% |
| LMArena Search | 1148 | 1142 |
| METR Time Horizons | 66.8% | 55.4% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| τ²-bench Banking | — | 13.7% |
| Cybench | 42% | — |
| BALROG | — | 43.3% |
| Vending-Bench 2 | — | 573.64 |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 31.6 (#70), Gemini 2.5 Pro: 28.8 (#85)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| SimpleBench | 60% | 62.4% |
| Chess Puzzles | 7% | 20% |
| EnigmaEval | 7.2% | 5.6% |
| LMArena Hard Prompts | 1443 | 1455 |
| DTBench | 80% | 82.4% |
| LMCA | 37.1% | 34.8% |
| Epoch Capabilities Index | 144.11 | 145.32 |
| ForecastBench | 62 | 61.3 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 41% |
| CritPt | — | 2% |
| EBR-Bench | 7.9% | — |
| LiveBench Reasoning | — | 89.8% |
| Mystery Game Puzzles | 21% | — |
| LiveBench Data Analysis | — | 79.9% |
| LiveBench | — | 82.3% |
Math Gemini 2.5 Pro leads
Claude Opus 4.1: 22.0 (#267), Gemini 2.5 Pro: 31.9 (#191)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 24.6% |
| FrontierMath Tier 4 | 2.4% | 0% |
| OTIS Mock AIME 2024-2025 | 68.9% | 84.7% |
| LMArena Math | 1430 | 1450 |
| FrontierMath (Feb 2025 set) | 7.2% | 14.1% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| Omni-MATH | — | 41.6% |
| LiveBench Math | — | 90.2% |
| MATH Level 5 | — | 95.9% |
Knowledge Gemini 2.5 Pro leads
Claude Opus 4.1: 41.9 (#93), Gemini 2.5 Pro: 55.8 (#41)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| GPQA Diamond | 77.3% | 85.3% |
| Humanity's Last Exam | 11.5% | 21.6% |
| Confabulations | 17.1% | 10.6% |
| Vectara Hallucination Rate | 11.8% | 7% |
| LMArena Expert | 1439 | 1452 |
| MMLU-Pro | — | 86.3% |
| GPQA (HELM) | — | 74.9% |
Multimodal Gemini 2.5 Pro leads
Claude Opus 4.1: 26.2 (#114), Gemini 2.5 Pro: 44.5 (#16)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| VPCT | 35% | 48% |
| LMArena Vision | — | 1263 |
| GeoBench | — | 86% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
Claude Opus 4.1: 52.1 (#90), Gemini 2.5 Pro: 55.5 (#30)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1405 | 1452 |
| LMArena Chinese | 1427 | 1507 |
| LMArena French | 1432 | 1473 |
| LMArena German | 1412 | 1487 |
| LMArena Japanese | 1378 | 1462 |
| LMArena Korean | 1381 | 1435 |
| LMArena Russian | 1421 | 1460 |
| LMArena Spanish | 1448 | 1473 |
Instruction Following Too close to call
Claude Opus 4.1: 75.8 (#53), Gemini 2.5 Pro: 75.2 (#71)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1436 | 1436 |
| LiveBench Instruction Following | — | 80.6% |
| IFEval | — | 84% |
Long Context Gemini 2.5 Pro leads
Claude Opus 4.1: 44.5 (#60), Gemini 2.5 Pro: 59.7 (#5)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1455 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
Claude Opus 4.1: 62.6 (#70), Gemini 2.5 Pro: 63.9 (#60)
| Benchmark | Claude Opus 4.1 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1419 | 1458 |
| LMArena Creative Writing | 1412 | 1453 |
| Short-Story Creative Writing | 84.7% | 83.8% |
| LMArena Multi-Turn | 1444 | 1453 |
| EQ-Bench Creative Writing | — | 1421 |
| WildBench | — | 85.7% |
| LiveBench Language | — | 67.8% |
Frequently asked questions
Is Claude Opus 4.1 better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.8 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Gemini 2.5 Pro?
Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Gemini 2.5 Pro better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 42.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Gemini 2.5 Pro share?
45 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Gemini 2.5 Pro has 78.