Model comparison
GPT-4 vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2-Pro leads 39.5 to 10.8.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $30 / $60 for GPT-4.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 8K.
Side by side
| GPT-4 | MiMo-V2-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 29.1 | 43.0 |
| Released | 2023-03-14 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $30 | $0.43 |
| Output $ / M tokens | $60 | $0.87 |
| Results tracked | 38 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
GPT-4: 31.6 (#283), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1254 | 1476 |
| LMArena WebDev | — | 1433 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 785.17 |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, MiMo-V2-Pro: —
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning MiMo-V2-Pro leads
GPT-4: 17.8 (#289), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Chess Puzzles | 4% | — |
| Thematic Generalization | — | 45.9% |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math MiMo-V2-Pro leads
GPT-4: 10.8 (#309), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1269 | 1447 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge MiMo-V2-Pro leads
GPT-4: 18.4 (#282), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1211 | 1478 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual MiMo-V2-Pro leads
GPT-4: 40.6 (#215), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1246 | 1416 |
| LMArena Chinese | 1242 | 1456 |
| LMArena French | 1283 | 1469 |
| LMArena German | 1251 | 1417 |
| LMArena Japanese | 1209 | 1366 |
| LMArena Korean | 1184 | 1400 |
| LMArena Russian | 1251 | 1427 |
| LMArena Spanish | 1261 | 1457 |
Instruction Following MiMo-V2-Pro leads
GPT-4: 65.3 (#222), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1241 | 1445 |
Long Context MiMo-V2-Pro leads
GPT-4: 37.7 (#212), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1244 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
GPT-4: 34.9 (#268), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | GPT-4 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1263 | 1436 |
| LMArena Creative Writing | 1244 | 1415 |
| LMArena Multi-Turn | 1257 | 1456 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 8K.
How many benchmarks do GPT-4 and MiMo-V2-Pro share?
17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiMo-V2-Pro has 23.