# GPT-5 vs MiMo-V2-Pro

> GPT-5 is the stronger model overall, scoring 50.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 6.3× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-vs-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-5 scores higher in 6 categories and MiMo-V2-Pro in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 41.5.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.25 / $10 for GPT-5.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 50.9 | 43.0 |
| Rank | 45 | 103 |
| Context | 400K | 1.05M |
| Input $/M | $1.25 | $0.43 |
| Output $/M | $10 | $0.87 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5: 50.3 (#47)
- MiMo-V2-Pro: 43.8 (#83)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1418 | 1433 |
| LMArena Coding | 1436 | 1476 |
| ALE-Bench | 1,162 | 785.17 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| WeirdML | 60.7% | — |
| AlgoTune | 1.67 | — |

## Agentic & Tool Use

- GPT-5: 33.1 (#56)
- MiMo-V2-Pro: —

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |

## Reasoning

- GPT-5: 38.3 (#64)
- MiMo-V2-Pro: 22.1 (#206)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1457 |
| ARC-AGI-2 | 9.9% | — |
| SimpleBench | 56.7% | — |
| Kagi LLM Benchmark | 72.7% | — |
| NYT Connections (extended) | — | 25.8% |
| ARC-AGI-1 | 65.7% | — |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| Thematic Generalization | — | 45.9% |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LMCA | 40% | — |
| Epoch Capabilities Index | 150 | — |
| ForecastBench | 61.4 | — |

## Math

- GPT-5: 55.0 (#44)
- MiMo-V2-Pro: 39.5 (#102)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1407 | 1447 |
| FrontierMath (Tiers 1-3) | 55.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GPT-5: 56.6 (#43)
- MiMo-V2-Pro: 41.4 (#111)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1419 | 1478 |
| GPQA Diamond | 86.2% | — |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |

## Multimodal

- GPT-5: 46.8 (#13)
- MiMo-V2-Pro: —

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |

## Multilingual

- GPT-5: 51.4 (#110)
- MiMo-V2-Pro: 52.7 (#81)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1397 | 1416 |
| LMArena Chinese | 1422 | 1456 |
| LMArena French | 1410 | 1469 |
| LMArena German | 1416 | 1417 |
| LMArena Japanese | 1409 | 1366 |
| LMArena Korean | 1360 | 1400 |
| LMArena Russian | 1406 | 1427 |
| LMArena Spanish | 1399 | 1457 |

## Instruction Following

- GPT-5: 73.8 (#113)
- MiMo-V2-Pro: 76.0 (#49)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1388 | 1445 |
| IFEval | 87.5% | — |

## Long Context

- GPT-5: 69.5 (#2)
- MiMo-V2-Pro: 41.5 (#138)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1399 | 1455 |
| Fiction.LiveBench | 97.2% | — |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- GPT-5: 63.4 (#65)
- MiMo-V2-Pro: 62.8 (#70)

| Benchmark | GPT-5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1406 | 1436 |
| LMArena Creative Writing | 1365 | 1415 |
| LMArena Multi-Turn | 1426 | 1456 |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |

## FAQ

### Is GPT-5 better than MiMo-V2-Pro?

GPT-5 is the stronger model overall, scoring 50.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 6.3× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

### Which is cheaper, GPT-5 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-5 lists at $1.25 and $10.

### Is GPT-5 or MiMo-V2-Pro better for coding?

GPT-5 scores higher on coding benchmarks: 50.3 versus 43.8 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 400K.

### How many benchmarks do GPT-5 and MiMo-V2-Pro share?

19 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and MiMo-V2-Pro has 23.