Model comparison
GPT-4.1 mini vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 33.6 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GPT-4.1 mini 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 coding, where MiMo-V2.5-Pro leads 47.4 to 30.6.
- The biggest single-benchmark swing is DTBench: 68.8% for GPT-4.1 mini 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 $0.40 / $1.60 for GPT-4.1 mini.
- 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 mini | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 33.6 | 45.2 |
| Released | 2025-04-14 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.40 | $0.43 |
| Output $ / M tokens | $1.60 | $0.87 |
| Results tracked | 47 | 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 mini: 30.6 (#293), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 40.4% | 50.2% |
| LMArena Coding | 1367 | 1503 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1479 |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
GPT-4.1 mini: 33.3 (#55), MiMo-V2.5-Pro: —
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
Reasoning MiMo-V2.5-Pro leads
GPT-4.1 mini: 10.8 (#340), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1349 | 1488 |
| DTBench | 68.8% | 84.5% |
| LMCA | 21.1% | 29.5% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 3.5% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| Epoch Capabilities Index | 135.01 | — |
Math MiMo-V2.5-Pro leads
GPT-4.1 mini: 24.1 (#270), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1343 | 1481 |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| OTIS Mock AIME 2024-2025 | 44.7% | — |
| ProofBench | — | 22% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge MiMo-V2.5-Pro leads
GPT-4.1 mini: 34.7 (#194), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1338 | 1503 |
| GPQA Diamond | 65.8% | — |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal Not comparable
GPT-4.1 mini: 35.8 (#82), MiMo-V2.5-Pro: —
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1181 | — |
Multilingual MiMo-V2.5-Pro leads
GPT-4.1 mini: 45.7 (#166), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1318 | 1449 |
| LMArena Chinese | 1329 | 1507 |
| LMArena French | 1358 | 1488 |
| LMArena German | 1351 | 1458 |
| LMArena Japanese | 1290 | 1412 |
| LMArena Korean | 1298 | 1437 |
| LMArena Russian | 1324 | 1450 |
| LMArena Spanish | 1319 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
GPT-4.1 mini: 73.7 (#118), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1333 | 1477 |
| IFEval | 90.4% | — |
Long Context MiMo-V2.5-Pro leads
GPT-4.1 mini: 31.8 (#275), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1344 | 1483 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference MiMo-V2.5-Pro leads
GPT-4.1 mini: 48.6 (#199), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | GPT-4.1 mini | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1340 | 1465 |
| LMArena Creative Writing | 1300 | 1440 |
| EQ-Bench Creative Writing | 1147 | 1493 |
| LMArena Multi-Turn | 1354 | 1477 |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-4.1 mini better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 33.6 on the Noometry Index.
Which is cheaper, GPT-4.1 mini 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 mini lists at $0.40 and $1.60.
Is GPT-4.1 mini or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 30.6 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 mini and MiMo-V2.5-Pro share?
22 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and MiMo-V2.5-Pro has 27.