Model comparison
Claude Opus 4 vs Gemini 3.5 Flash
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 43.1 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Claude Opus 4 scores higher in 2 categories and Gemini 3.5 Flash in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.8 to 27.3.
- The biggest single-benchmark swing is ARC-AGI-2: 8.6% for Claude Opus 4 and 72.1% for Gemini 3.5 Flash.
- Gemini 3.5 Flash is cheaper at $1.50 / $9 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4 | Gemini 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 43.1 | 54.2 |
| Released | 2025-05-22 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 66K |
| Input $ / M tokens | $15 | $1.50 |
| Output $ / M tokens | $75 | $9 |
| Results tracked | 56 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash leads
Claude Opus 4: 47.2 (#62), Gemini 3.5 Flash: 49.4 (#49)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| SWE-bench Verified | 70.7% | 79.3% |
| WeirdML | 43.7% | 62.6% |
| LMArena Coding | 1442 | 1492 |
| DeepSWE | — | 37.4% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1499 |
| SciCode | — | 53.1% |
| GSO | 6.9% | — |
| ALE-Bench | — | 911.02 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Gemini 3.5 Flash: 24.7 (#114)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| APEX-Agents | — | 27.5% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| GBAEval | — | 6.7% |
| GDP.pdf | — | 14% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 5,396 |
Reasoning Gemini 3.5 Flash leads
Claude Opus 4: 27.3 (#121), Gemini 3.5 Flash: 62.8 (#18)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| ARC-AGI-2 | 8.6% | 72.1% |
| SimpleBench | 58.8% | 76.7% |
| ARC-AGI-1 | 35.7% | 92.5% |
| CritPt | 0.3% | 13.1% |
| EnigmaEval | 5.6% | 25.4% |
| LMArena Hard Prompts | 1399 | 1488 |
| DTBench | 81.6% | 94.7% |
| LMCA | 37.4% | 47.1% |
| Epoch Capabilities Index | 142.67 | 154.46 |
| ForecastBench | 61.1 | 59 |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 92.6% |
| Chess Puzzles | — | 50% |
| EBR-Bench | — | 4.8% |
| Mystery Game Puzzles | — | 32% |
| Surface Evolver Bench | — | 58.1% |
Math Gemini 3.5 Flash leads
Claude Opus 4: 42.0 (#86), Gemini 3.5 Flash: 60.7 (#36)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 95.6% |
| LMArena Math | 1390 | 1504 |
| FrontierMath (Feb 2025 set) | 4.5% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 62.8% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.3% |
| ProofBench | — | 31% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
Knowledge Gemini 3.5 Flash leads
Claude Opus 4: 44.0 (#88), Gemini 3.5 Flash: 66.3 (#11)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| GPQA Diamond | 76.3% | 92.8% |
| LMArena Expert | 1386 | 1495 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 66.2% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Gemini 3.5 Flash leads
Claude Opus 4: 31.5 (#106), Gemini 3.5 Flash: 45.7 (#15)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Vision | 1192 | 1310 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| Blueprint-Bench 2 | — | 33.6% |
| LMArena Document | — | 1463 |
Multilingual Gemini 3.5 Flash leads
Claude Opus 4: 48.8 (#138), Gemini 3.5 Flash: 57.0 (#13)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1362 | 1476 |
| LMArena Chinese | 1386 | 1526 |
| LMArena French | 1372 | 1490 |
| LMArena German | 1391 | 1492 |
| LMArena Japanese | 1331 | 1486 |
| LMArena Korean | 1321 | 1451 |
| LMArena Russian | 1392 | 1493 |
| LMArena Spanish | 1389 | 1480 |
Instruction Following Too close to call
Claude Opus 4: 77.1 (#28), Gemini 3.5 Flash: 77.0 (#30)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1467 |
| IFEval | 91.8% | — |
Long Context Gemini 3.5 Flash leads
Claude Opus 4: 39.6 (#172), Gemini 3.5 Flash: 45.4 (#38)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1422 | 1482 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 3.5 Flash leads
Claude Opus 4: 61.2 (#89), Gemini 3.5 Flash: 65.5 (#47)
| Benchmark | Claude Opus 4 | Gemini 3.5 Flash |
|---|---|---|
| LMArena Text | 1377 | 1482 |
| LMArena Creative Writing | 1387 | 1470 |
| LMArena Multi-Turn | 1396 | 1481 |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
| EQ-Bench 4 | — | 1087 |
Frequently asked questions
Is Claude Opus 4 better than Gemini 3.5 Flash?
Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or Gemini 3.5 Flash?
Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Gemini 3.5 Flash better for coding?
Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4 and Gemini 3.5 Flash share?
33 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Gemini 3.5 Flash has 54.