Model comparison
Claude Opus 4 vs Gemini 2.5 Flash
Claude Opus 4 is the stronger model overall, scoring 43.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 35× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 47 shared benchmarks.
GoogleSummary
- They share 47 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and Gemini 2.5 Flash in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.2 to 35.8.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 67.6% for Claude Opus 4 and 28.7% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4 | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 43.1 | 39.3 |
| Released | 2025-05-22 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 66K |
| Input $ / M tokens | $15 | $0.30 |
| Output $ / M tokens | $75 | $2.50 |
| Results tracked | 56 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| SWE-bench Verified (bash only) | 67.6% | 28.7% |
| Aider Polyglot | 72% | 55.1% |
| WeirdML | 43.7% | 41.9% |
| LMArena Coding | 1442 | 1424 |
| SWE-bench Verified | 70.7% | — |
| GSO | 6.9% | — |
| ALE-Bench | — | 661.88 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| BALROG | — | 33.5% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 548.84 |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| ARC-AGI-2 | 8.6% | 2.5% |
| SimpleBench | 58.8% | 41.2% |
| Kagi LLM Benchmark | 74.3% | 56.8% |
| ARC-AGI-1 | 35.7% | 33.3% |
| CritPt | 0.3% | 1.1% |
| EnigmaEval | 5.6% | 2.7% |
| LMArena Hard Prompts | 1399 | 1422 |
| DTBench | 81.6% | 76.5% |
| LMCA | 37.4% | 27.5% |
| Epoch Capabilities Index | 142.67 | 143.03 |
| ForecastBench | 61.1 | 60.6 |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 73.1% |
| Omni-MATH | 61.6% | 38.5% |
| LMArena Math | 1390 | 1415 |
| FrontierMath (Feb 2025 set) | 4.5% | 4.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| MATH Level 5 | 85% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| Humanity's Last Exam | 10.7% | 12.1% |
| MMLU-Pro | 87.5% | 63.9% |
| Confabulations | 15.9% | 16.8% |
| Vectara Hallucination Rate | 12% | 7.8% |
| GPQA (HELM) | 70.8% | 39% |
| LMArena Expert | 1386 | 1426 |
| GPQA Diamond | 76.3% | — |
Multimodal Gemini 2.5 Flash leads
Claude Opus 4: 31.5 (#106), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 1192 | 1253 |
| GeoBench | 49% | 76% |
| VPCT | 38% | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Claude Opus 4: 48.8 (#138), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1362 | 1409 |
| LMArena Chinese | 1386 | 1450 |
| LMArena French | 1372 | 1433 |
| LMArena German | 1391 | 1418 |
| LMArena Japanese | 1331 | 1405 |
| LMArena Korean | 1321 | 1385 |
| LMArena Russian | 1392 | 1415 |
| LMArena Spanish | 1389 | 1421 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 91.8% | 89.8% |
| LMArena Instruction Following | 1406 | 1405 |
Long Context Gemini 2.5 Flash leads
Claude Opus 4: 39.6 (#172), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| Fiction.LiveBench | 61.1% | 77.8% |
| LMArena Longer Query | 1422 | 1419 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Claude Opus 4 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1377 | 1417 |
| LMArena Creative Writing | 1387 | 1400 |
| Short-Story Creative Writing | 83.6% | 76.5% |
| EQ-Bench Creative Writing | 1580 | 1137 |
| WildBench | 85.2% | 81.7% |
| LMArena Multi-Turn | 1396 | 1408 |
Frequently asked questions
Is Claude Opus 4 better than Gemini 2.5 Flash?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 35× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Gemini 2.5 Flash better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4 and Gemini 2.5 Flash share?
47 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Gemini 2.5 Flash has 54.