Model comparison
GPT-5 Nano vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GPT-5 Nano scores higher in 0 categories and MiMo-V2.5 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 39.4.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- 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 Nano | MiMo-V2.5 | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 33.4 | 43.0 |
| Released | 2025-08-07 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.05 | $0.14 |
| Output $ / M tokens | $0.40 | $0.28 |
| Results tracked | 48 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
GPT-5 Nano: 33.3 (#248), MiMo-V2.5: 43.6 (#75)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1351 | 1469 |
| ALE-Bench | 718.67 | 513.95 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| WeirdML | 38.1% | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.6 (#99), MiMo-V2.5: —
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning MiMo-V2.5 leads
GPT-5 Nano: 16.4 (#291), MiMo-V2.5: 27.8 (#98)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1450 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 3.7% |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.39 | — |
| ForecastBench | 59.1 | — |
Math MiMo-V2.5 leads
GPT-5 Nano: 29.1 (#221), MiMo-V2.5: 35.4 (#145)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| ProofBench | 12% | 16% |
| LMArena Math | 1318 | 1436 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge MiMo-V2.5 leads
GPT-5 Nano: 35.8 (#166), MiMo-V2.5: 40.2 (#109)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1321 | 1459 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal MiMo-V2.5 leads
GPT-5 Nano: 30.7 (#102), MiMo-V2.5: 39.0 (#53)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1159 | 1245 |
| VPCT | 37.2% | — |
Multilingual MiMo-V2.5 leads
GPT-5 Nano: 45.5 (#167), MiMo-V2.5: 52.0 (#96)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1313 | 1404 |
| LMArena Chinese | 1355 | 1467 |
| LMArena German | 1329 | 1421 |
| LMArena Korean | 1269 | 1363 |
| LMArena Russian | 1296 | 1395 |
| LMArena Spanish | 1360 | 1412 |
| LMArena French | — | 1447 |
| LMArena Japanese | — | 1304 |
Instruction Following Too close to call
GPT-5 Nano: 75.2 (#72), MiMo-V2.5: 75.7 (#55)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1433 |
| IFEval | 93.2% | — |
Long Context MiMo-V2.5 leads
GPT-5 Nano: 31.3 (#275), MiMo-V2.5: 44.1 (#69)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1313 | 1444 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference MiMo-V2.5 leads
GPT-5 Nano: 39.4 (#244), MiMo-V2.5: 61.8 (#82)
| Benchmark | GPT-5 Nano | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1320 | 1427 |
| LMArena Creative Writing | 1250 | 1392 |
| LMArena Multi-Turn | 1311 | 1445 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.
Which is cheaper, GPT-5 Nano or MiMo-V2.5?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.
Is GPT-5 Nano or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 33.3 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 Nano and MiMo-V2.5 share?
18 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and MiMo-V2.5 has 23.