Model comparison
GPT-5 Mini vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 41.8 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GPT-5 Mini scores higher in 3 categories and MiMo-V2.5 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 36.8.
- The biggest single-benchmark swing is ProofBench: 9% for GPT-5 Mini and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 400K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | MiMo-V2.5 | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 41.8 | 43.4 |
| Released | 2025-08-07 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.25 | $0.14 |
| Output $ / M tokens | $2 | $0.28 |
| Results tracked | 60 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
GPT-5 Mini: 40.1 (#146), MiMo-V2.5: 43.9 (#81)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| SciCode | 39.2% | 43.1% |
| LMArena Coding | 1406 | 1469 |
| ALE-Bench | 799.77 | 513.95 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1438 |
| SWE-bench Multilingual | 39.7% | — |
| WeirdML | 52.7% | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), MiMo-V2.5: —
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning MiMo-V2.5 leads
GPT-5 Mini: 23.9 (#168), MiMo-V2.5: 28.6 (#101)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1380 | 1450 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), MiMo-V2.5: 36.8 (#163)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| ProofBench | 9% | 16% |
| LMArena Math | 1378 | 1436 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), MiMo-V2.5: 40.8 (#115)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1379 | 1460 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal MiMo-V2.5 leads
GPT-5 Mini: 35.6 (#85), MiMo-V2.5: 39.8 (#54)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1202 | 1247 |
| VPCT | 40.2% | — |
Multilingual MiMo-V2.5 leads
GPT-5 Mini: 48.9 (#137), MiMo-V2.5: 51.9 (#99)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1363 | 1404 |
| LMArena Chinese | 1385 | 1468 |
| LMArena French | 1386 | 1447 |
| LMArena German | 1366 | 1421 |
| LMArena Japanese | 1341 | 1306 |
| LMArena Korean | 1308 | 1363 |
| LMArena Russian | 1362 | 1395 |
| LMArena Spanish | 1355 | 1416 |
Instruction Following Too close to call
GPT-5 Mini: 76.2 (#46), MiMo-V2.5: 75.5 (#60)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1434 |
| IFEval | 92.7% | — |
Long Context MiMo-V2.5 leads
GPT-5 Mini: 41.9 (#132), MiMo-V2.5: 44.2 (#73)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1355 | 1445 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference MiMo-V2.5 leads
GPT-5 Mini: 55.2 (#148), MiMo-V2.5: 61.6 (#86)
| Benchmark | GPT-5 Mini | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1373 | 1428 |
| LMArena Creative Writing | 1325 | 1393 |
| LMArena Multi-Turn | 1363 | 1445 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 41.8 on the Noometry Index.
Which is cheaper, GPT-5 Mini or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5 Mini and MiMo-V2.5 share?
22 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and MiMo-V2.5 has 23.