# Gemini 2.5 Flash vs GPT-5.1

> GPT-5.1 is the stronger model overall, scoring 48.8 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 4.0× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-gpt-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 43

## Summary

- They share 43 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 0 categories and GPT-5.1 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.9 to 18.2.
- The biggest single-benchmark swing is ARC-AGI-1: 33.3% for Gemini 2.5 Flash and 72.8% for GPT-5.1.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 39.0 | 48.8 |
| Rank | 162 | 47 |
| Context | 1.05M | 400K |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $2.50 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash: 35.5 (#210)
- GPT-5.1: 46.9 (#59)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 66% |
| WeirdML | 41.9% | 60.8% |
| LMArena Coding | 1424 | 1454 |
| ALE-Bench | 661.88 | 1,192 |
| SWE-bench Verified | — | 68% |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| LiveBench Coding | — | 72.5% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.6 (#67)
- GPT-5.1: 32.5 (#55)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| Terminal-Bench | 17.1% | 47.6% |
| Vending-Bench 2 | 548.84 | 1,473 |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| DeepResearch Bench | — | 42.8% |
| BALROG | 33.5% | — |
| LMArena Search | — | 1199 |

## Reasoning

- Gemini 2.5 Flash: 18.2 (#271)
- GPT-5.1: 39.9 (#50)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 2.5% | 17.6% |
| SimpleBench | 41.2% | 53.2% |
| ARC-AGI-1 | 33.3% | 72.8% |
| CritPt | 1.1% | 4.9% |
| EnigmaEval | 2.7% | 11.2% |
| LMArena Hard Prompts | 1422 | 1457 |
| DTBench | 76.5% | 90.1% |
| LMCA | 27.5% | 43.9% |
| Epoch Capabilities Index | 143.04 | 149.66 |
| ForecastBench | 60.6 | 58.1 |
| Kagi LLM Benchmark | 56.8% | — |
| Chess Puzzles | — | 32% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | — | 72.1% |
| LiveBench | — | 78.8% |

## Math

- Gemini 2.5 Flash: 38.1 (#87)
- GPT-5.1: 50.3 (#45)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 88.6% |
| Omni-MATH | 38.5% | 46.4% |
| LMArena Math | 1415 | 1446 |
| FrontierMath (Feb 2025 set) | 4.8% | 31% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| LiveBench Math | — | 94.5% |

## Knowledge

- Gemini 2.5 Flash: 36.1 (#162)
- GPT-5.1: 50.5 (#65)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| Humanity's Last Exam | 12.1% | 23.7% |
| MMLU-Pro | 63.9% | 57.9% |
| Vectara Hallucination Rate | 7.8% | 10.9% |
| GPQA (HELM) | 39% | 44.2% |
| LMArena Expert | 1426 | 1470 |
| GPQA Diamond | — | 87.6% |
| SimpleQA Verified | — | 48% |
| Confabulations | 16.8% | — |

## Multimodal

- Gemini 2.5 Flash: 41.2 (#31)
- GPT-5.1: 44.0 (#17)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1254 | 1250 |
| VPCT | 46.2% | 58.7% |
| GeoBench | 76% | — |
| LMArena Document | — | 1403 |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.5 (#83)
- GPT-5.1: 54.0 (#51)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1410 | 1431 |
| LMArena Chinese | 1450 | 1495 |
| LMArena French | 1433 | 1451 |
| LMArena German | 1419 | 1439 |
| LMArena Japanese | 1403 | 1453 |
| LMArena Korean | 1385 | 1401 |
| LMArena Russian | 1415 | 1435 |
| LMArena Spanish | 1421 | 1430 |

## Instruction Following

- Gemini 2.5 Flash: 75.9 (#50)
- GPT-5.1: 84.0 (#1)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| IFEval | 89.8% | 93.5% |
| LMArena Instruction Following | 1405 | 1442 |
| LiveBench Instruction Following | — | 93.3% |

## Long Context

- Gemini 2.5 Flash: 47.5 (#16)
- GPT-5.1: 47.6 (#14)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1419 | 1448 |
| Fiction.LiveBench | 77.8% | — |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- Gemini 2.5 Flash: 54.0 (#153)
- GPT-5.1: 64.7 (#53)

| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Text | 1417 | 1443 |
| LMArena Creative Writing | 1400 | 1427 |
| WildBench | 81.7% | 86.3% |
| LMArena Multi-Turn | 1408 | 1449 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| LiveBench Language | — | 80.2% |

## FAQ

### Is Gemini 2.5 Flash better than GPT-5.1?

GPT-5.1 is the stronger model overall, scoring 48.8 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 4.0× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash or GPT-5.1?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.1 lists at $1.25 and $10.

### Is Gemini 2.5 Flash or GPT-5.1 better for coding?

GPT-5.1 scores higher on coding benchmarks: 46.9 versus 35.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 400K.

### How many benchmarks do Gemini 2.5 Flash and GPT-5.1 share?

43 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-5.1 has 63.