Model comparison
Gemini 2.5 Flash vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 39.3 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.
Last verified . 43 shared benchmarks.
GoogleSummary
- 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 39.8 to 18.1.
- 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.
Side by side
| Gemini 2.5 Flash | GPT-5.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 49.0 |
| Released | 2025-04-17 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $2.50 | $10 |
| Results tracked | 54 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
Gemini 2.5 Flash: 35.8 (#220), GPT-5.1: 46.4 (#66)
| 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 GPT-5.1 leads
Gemini 2.5 Flash: 30.8 (#74), GPT-5.1: 32.7 (#60)
| 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 GPT-5.1 leads
Gemini 2.5 Flash: 18.1 (#286), GPT-5.1: 39.8 (#58)
| 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 | 143.03 | 149.64 |
| 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 GPT-5.1 leads
Gemini 2.5 Flash: 39.9 (#98), GPT-5.1: 52.2 (#51)
| 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 | 1447 |
| FrontierMath (Feb 2025 set) | 4.8% | 31% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| LiveBench Math | — | 94.5% |
Knowledge GPT-5.1 leads
Gemini 2.5 Flash: 36.4 (#168), GPT-5.1: 50.6 (#71)
| 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 GPT-5.1 leads
Gemini 2.5 Flash: 41.8 (#32), GPT-5.1: 44.8 (#19)
| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1253 | 1250 |
| VPCT | 46.2% | 58.7% |
| GeoBench | 76% | — |
| LMArena Document | — | 1403 |
| SpatialViz-Bench | 36.9% | — |
Multilingual GPT-5.1 leads
Gemini 2.5 Flash: 52.3 (#88), GPT-5.1: 53.8 (#56)
| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1409 | 1431 |
| LMArena Chinese | 1450 | 1495 |
| LMArena French | 1433 | 1450 |
| LMArena German | 1418 | 1438 |
| LMArena Japanese | 1405 | 1453 |
| LMArena Korean | 1385 | 1401 |
| LMArena Russian | 1415 | 1435 |
| LMArena Spanish | 1421 | 1433 |
Instruction Following GPT-5.1 leads
Gemini 2.5 Flash: 75.7 (#54), GPT-5.1: 83.9 (#1)
| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| IFEval | 89.8% | 93.5% |
| LMArena Instruction Following | 1405 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
Long Context Too close to call
Gemini 2.5 Flash: 47.5 (#17), GPT-5.1: 47.6 (#14)
| Benchmark | Gemini 2.5 Flash | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1419 | 1447 |
| Fiction.LiveBench | 77.8% | — |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Gemini 2.5 Flash: 53.8 (#157), GPT-5.1: 64.5 (#55)
| 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 | 1450 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is Gemini 2.5 Flash better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 39.3 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: 46.4 versus 35.8 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.