Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.7 to 34.8 on the Noometry Index.
Last verified . 39 shared benchmarks.
GoogleSummary
- They share 39 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and GPT-5 Mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.5 to 32.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 59.8% for GPT-5 Mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 34.8 | 41.7 |
| Released | 2024-12-06 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 54 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 28.2 (#308), GPT-5 Mini: 40.0 (#134)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 59.8% |
| WeirdML | 25.8% | 52.7% |
| LMArena Coding | 1351 | 1406 |
| SWE-bench Verified | — | 64.7% |
| Aider Polyglot | 38.2% | — |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), GPT-5 Mini: 31.0 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| TheAgentCompany | 11.4% | — |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), GPT-5 Mini: 24.1 (#153)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 4.4% |
| Kagi LLM Benchmark | 37.8% | 70.3% |
| EnigmaEval | 1.1% | 8.2% |
| LMArena Hard Prompts | 1346 | 1380 |
| DTBench | 63.2% | 80.5% |
| Epoch Capabilities Index | 135.36 | 145.51 |
| SimpleBench | 31.1% | — |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 10% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 34.2% |
| ForecastBench | — | 61 |
| LiveBench | 66.9% | — |
Math GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), GPT-5 Mini: 46.3 (#59)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 86.7% |
| Omni-MATH | 45.9% | 72.2% |
| LMArena Math | 1351 | 1377 |
| MATH Level 5 | 82.2% | 97.8% |
| FrontierMath (Feb 2025 set) | 1.7% | 27.2% |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 9% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), GPT-5 Mini: 45.5 (#80)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 64.1% | 75% |
| Humanity's Last Exam | 6.6% | 19.4% |
| MMLU-Pro | 73.7% | 83.5% |
| Confabulations | 12.4% | 13.3% |
| GPQA (HELM) | 55.6% | 75.6% |
| LMArena Expert | 1340 | 1377 |
| SimpleQA Verified | — | 21.6% |
| Vectara Hallucination Rate | — | 12.9% |
| MMLU | 79.7% | — |
Multimodal Too close to call
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), GPT-5 Mini: 35.0 (#80)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1158 | 1202 |
| GeoBench | 77% | — |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), GPT-5 Mini: 49.1 (#131)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1342 | 1363 |
| LMArena Chinese | 1373 | 1387 |
| LMArena French | 1390 | 1385 |
| LMArena German | 1354 | 1366 |
| LMArena Japanese | 1293 | 1342 |
| LMArena Korean | 1314 | 1306 |
| LMArena Russian | 1351 | 1362 |
| LMArena Spanish | 1363 | 1355 |
Instruction Following GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), GPT-5 Mini: 76.4 (#43)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| IFEval | 84.1% | 92.7% |
| LMArena Instruction Following | 1336 | 1357 |
| LiveBench Instruction Following | 85.8% | — |
Long Context GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), GPT-5 Mini: 41.9 (#127)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| Fiction.LiveBench | 61.1% | 69.4% |
| LMArena Longer Query | 1345 | 1355 |
Writing & Preference GPT-5 Mini leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), GPT-5 Mini: 55.4 (#143)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1354 | 1373 |
| LMArena Creative Writing | 1340 | 1325 |
| Short-Story Creative Writing | 73.8% | 83.1% |
| EQ-Bench Creative Writing | 1128 | 1313 |
| WildBench | 80% | 85.5% |
| LMArena Multi-Turn | 1350 | 1363 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 34.8 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 28.2 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-5 Mini share?
39 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-5 Mini has 60.