# Claude Opus 5.5 vs Gemini 2.5 Flash

> Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 9.4× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-gemini-2-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude Opus 5.5 scores higher in 9 categories and Gemini 2.5 Flash in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 79.5 to 18.2.
- The biggest single-benchmark swing is ARC-AGI-2: 92.5% for Claude Opus 5.5 and 2.5% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 68.5 | 39.0 |
| Rank | 3 | 162 |
| Context | 1M | 1.05M |
| Input $/M | $4 | $0.30 |
| Output $/M | $20 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 5.5: 71.4 (#1)
- Gemini 2.5 Flash: 35.5 (#210)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1545 | 1424 |
| FrontierCode | 54.4% | — |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| CursorBench | 57.8% | — |
| LMArena WebDev | 1820 | — |
| FrontierSWE | 62.3% | — |
| SciCode | 66.9% | — |
| WeirdML | — | 41.9% |
| MirrorCode | 77.4% | — |
| ALE-Bench | — | 661.88 |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#13)
- Gemini 2.5 Flash: 30.6 (#67)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| APEX-Agents | 73.5% | — |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| GDP.pdf | 30.6% | — |
| Vending-Bench 2 | — | 548.84 |

## Reasoning

- Claude Opus 5.5: 79.5 (#2)
- Gemini 2.5 Flash: 18.2 (#271)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| ARC-AGI-2 | 92.5% | 2.5% |
| ARC-AGI-1 | 97.5% | 33.3% |
| CritPt | 31.7% | 1.1% |
| LMArena Hard Prompts | 1545 | 1422 |
| DTBench | 98.9% | 76.5% |
| LMCA | 68.2% | 27.5% |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| NYT Connections (extended) | 88.5% | — |
| EnigmaEval | — | 2.7% |
| EBR-Bench | 71.4% | — |
| Mystery Game Puzzles | 71% | — |
| Epoch Capabilities Index | — | 143.04 |
| ForecastBench | — | 60.6 |

## Math

- Claude Opus 5.5: 92.4 (#2)
- Gemini 2.5 Flash: 38.1 (#87)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 73.1% |
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 38.5% |
| LMArena Math | — | 1415 |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude Opus 5.5: 66.6 (#9)
- Gemini 2.5 Flash: 36.1 (#162)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Expert | 1564 | 1426 |
| GPQA Diamond | 90.6% | — |
| Humanity's Last Exam | — | 12.1% |
| SimpleQA Verified | 72.2% | — |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |

## Multimodal

- Claude Opus 5.5: 56.5 (#2)
- Gemini 2.5 Flash: 41.2 (#31)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1254 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| Furniture Assembly | 83.3% | — |
| SpatialViz-Bench | — | 36.9% |

## Multilingual

- Claude Opus 5.5: 59.8 (#1)
- Gemini 2.5 Flash: 52.5 (#83)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1513 | 1410 |
| LMArena Chinese | 1572 | 1450 |
| LMArena Russian | 1532 | 1415 |
| LMArena French | — | 1433 |
| LMArena German | — | 1419 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1385 |
| LMArena Spanish | — | 1421 |

## Instruction Following

- Claude Opus 5.5: 80.1 (#2)
- Gemini 2.5 Flash: 75.9 (#50)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1535 | 1405 |
| IFEval | — | 89.8% |

## Long Context

- Claude Opus 5.5: 47.3 (#18)
- Gemini 2.5 Flash: 47.5 (#16)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1540 | 1419 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Claude Opus 5.5: 78.7 (#3)
- Gemini 2.5 Flash: 54.0 (#153)

| Benchmark | Claude Opus 5.5 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1518 | 1417 |
| LMArena Creative Writing | 1538 | 1400 |
| EQ-Bench Creative Writing | 2050 | 1137 |
| LMArena Multi-Turn | 1520 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| WildBench | — | 81.7% |

## FAQ

### Is Claude Opus 5.5 better than Gemini 2.5 Flash?

Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 9.4× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5.5 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 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Gemini 2.5 Flash better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.4 versus 35.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Opus 5.5 and Gemini 2.5 Flash share?

18 benchmarks have published results for both models. Claude Opus 5.5 has 35 scored results on Noometry and Gemini 2.5 Flash has 54.