Model comparison
GPT-4.1 vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 35.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GPT-4.1 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 math, where MiMo-V2.5-Pro leads 38.6 to 21.4.
- The biggest single-benchmark swing is DTBench: 68.3% for GPT-4.1 and 84.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $8 for GPT-4.1.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 1.05M.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 35.7 | 44.8 |
| Released | 2025-04-14 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 33K | 131K |
| Input $ / M tokens | $2 | $0.43 |
| Output $ / M tokens | $8 | $0.87 |
| Results tracked | 52 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
GPT-4.1: 34.2 (#228), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1391 | 1502 |
| ALE-Bench | 558.1 | 899.8 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| WeirdML | 39% | — |
| CadEval | 42% | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.4 (#40), MiMo-V2.5-Pro: —
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning MiMo-V2.5-Pro leads
GPT-4.1: 11.7 (#334), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1487 |
| DTBench | 68.3% | 84.5% |
| LMCA | 25.6% | 29.5% |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 4% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| Epoch Capabilities Index | 136.79 | — |
| ForecastBench | 61.5 | — |
Math MiMo-V2.5-Pro leads
GPT-4.1: 21.4 (#269), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1369 | 1480 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| ProofBench | — | 22% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge MiMo-V2.5-Pro leads
GPT-4.1: 37.0 (#152), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1364 | 1501 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 37.5 (#66), MiMo-V2.5-Pro: —
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 72% | — |
Multilingual MiMo-V2.5-Pro leads
GPT-4.1: 49.6 (#128), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1370 | 1449 |
| LMArena Chinese | 1382 | 1507 |
| LMArena French | 1383 | 1489 |
| LMArena German | 1380 | 1455 |
| LMArena Japanese | 1320 | 1418 |
| LMArena Korean | 1339 | 1436 |
| LMArena Russian | 1377 | 1450 |
| LMArena Spanish | 1375 | 1470 |
Instruction Following MiMo-V2.5-Pro leads
GPT-4.1: 71.5 (#148), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1367 | 1477 |
| IFEval | 83.8% | — |
Long Context MiMo-V2.5-Pro leads
GPT-4.1: 40.0 (#158), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1385 | 1482 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference MiMo-V2.5-Pro leads
GPT-4.1: 57.8 (#120), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | GPT-4.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1383 | 1465 |
| LMArena Creative Writing | 1363 | 1440 |
| EQ-Bench Creative Writing | 1420 | 1493 |
| LMArena Multi-Turn | 1398 | 1477 |
| WildBench | 85.4% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-4.1 better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 35.7 on the Noometry Index.
Which is cheaper, GPT-4.1 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-4.1 and MiMo-V2.5-Pro share?
21 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and MiMo-V2.5-Pro has 27.