Model comparison
GPT-3.5-turbo vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 23.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and MiMo-V2.6-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 6.3.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 16K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 23.2 | 50.3 |
| Released | 2023-03-01 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 16K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.50 | $0.43 |
| Output $ / M tokens | $1.50 | $0.87 |
| Results tracked | 44 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
GPT-3.5-turbo: 23.9 (#331), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1136 | 1534 |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| ALE-Bench | — | 1,158 |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
| METR Time Horizons | 21.5% | — |
Reasoning MiMo-V2.6-Pro leads
GPT-3.5-turbo: 13.8 (#332), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1512 |
| CritPt | — | 26.6% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math MiMo-V2.6-Pro leads
GPT-3.5-turbo: 6.3 (#327), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1142 | 1494 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| ProofBench | — | 70% |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge MiMo-V2.6-Pro leads
GPT-3.5-turbo: 10.0 (#303), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1070 | 1543 |
| GPQA Diamond | 28% | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
GPT-3.5-turbo: 31.5 (#258), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1108 | 1474 |
| LMArena Chinese | 1075 | 1529 |
| LMArena Russian | 1123 | 1480 |
| LMArena French | 1118 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
| LMArena Spanish | 1121 | — |
Instruction Following MiMo-V2.6-Pro leads
GPT-3.5-turbo: 57.9 (#262), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1119 | 1493 |
Long Context MiMo-V2.6-Pro leads
GPT-3.5-turbo: 34.0 (#254), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1121 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
GPT-3.5-turbo: 25.3 (#305), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | GPT-3.5-turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1125 | 1492 |
| LMArena Creative Writing | 1092 | 1468 |
| LMArena Multi-Turn | 1117 | 1464 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 23.2 on the Noometry Index.
Which is cheaper, GPT-3.5-turbo or MiMo-V2.6-Pro?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.
Is GPT-3.5-turbo or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 16K.
How many benchmarks do GPT-3.5-turbo and MiMo-V2.6-Pro share?
12 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and MiMo-V2.6-Pro has 19.