Model comparison
GPT-5 Nano vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 33.4 on the Noometry Index. GPT-5 Nano costs 4.0× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-5 Nano scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 39.4.
- The biggest single-benchmark swing is DTBench: 62.7% for GPT-5 Nano and 84.5% for MiMo-V2.5-Pro.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 400K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 33.4 | 44.8 |
| Released | 2025-08-07 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.05 | $0.43 |
| Output $ / M tokens | $0.40 | $0.87 |
| Results tracked | 48 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
GPT-5 Nano: 33.3 (#248), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1351 | 1502 |
| ALE-Bench | 718.67 | 899.8 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| WeirdML | 38.1% | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.6 (#99), MiMo-V2.5-Pro: —
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning MiMo-V2.5-Pro leads
GPT-5 Nano: 16.4 (#291), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1487 |
| DTBench | 62.7% | 84.5% |
| LMCA | 7.9% | 29.5% |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 4% |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| Epoch Capabilities Index | 139.39 | — |
| ForecastBench | 59.1 | — |
Math MiMo-V2.5-Pro leads
GPT-5 Nano: 29.1 (#221), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 12% | 22% |
| LMArena Math | 1318 | 1480 |
| 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-Pro leads
GPT-5 Nano: 35.8 (#166), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1321 | 1501 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), MiMo-V2.5-Pro: —
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual MiMo-V2.5-Pro leads
GPT-5 Nano: 45.5 (#167), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1313 | 1449 |
| LMArena Chinese | 1355 | 1507 |
| LMArena German | 1329 | 1455 |
| LMArena Korean | 1269 | 1436 |
| LMArena Russian | 1296 | 1450 |
| LMArena Spanish | 1360 | 1470 |
| LMArena French | — | 1489 |
| LMArena Japanese | — | 1418 |
Instruction Following MiMo-V2.5-Pro leads
GPT-5 Nano: 75.2 (#72), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1306 | 1477 |
| IFEval | 93.2% | — |
Long Context MiMo-V2.5-Pro leads
GPT-5 Nano: 31.3 (#275), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1313 | 1482 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference MiMo-V2.5-Pro leads
GPT-5 Nano: 39.4 (#244), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | GPT-5 Nano | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1320 | 1465 |
| LMArena Creative Writing | 1250 | 1440 |
| EQ-Bench Creative Writing | 705 | 1493 |
| LMArena Multi-Turn | 1311 | 1477 |
| WildBench | 80.6% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-5 Nano better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 33.4 on the Noometry Index. GPT-5 Nano costs 4.0× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or MiMo-V2.5-Pro?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is GPT-5 Nano or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5 Nano and MiMo-V2.5-Pro share?
20 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and MiMo-V2.5-Pro has 27.