Model comparison
GPT-5.3 Codex vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 45.8 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.3 Codex scores higher in 1 category and MiMo-V2.6-Pro in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 37.5.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 400K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 45.8 | 50.3 |
| Released | 2026-02-05 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.75 | $0.43 |
| Output $ / M tokens | $14 | $0.87 |
| Results tracked | 8 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
GPT-5.3 Codex: 48.6 (#56), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1409 | 1629 |
| ALE-Bench | 1,655 | 1,158 |
| SWE-bench Verified | 74.8% | — |
| SciCode | — | 60.9% |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 1534 |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-5.3 Codex: 48.0 (#9), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| APEX-Agents | — | 59.5% |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | — | 26.6% |
| LMArena Hard Prompts | — | 1512 |
| Epoch Capabilities Index | 156.77 | — |
Math Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | — | 70% |
| LMArena Math | — | 1494 |
Knowledge Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | — | 1543 |
Multimodal Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1529 |
| LMArena Russian | — | 1480 |
Instruction Following Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1493 |
Long Context Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | — | 1501 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | GPT-5.3 Codex | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | — | 1492 |
| LMArena Creative Writing | — | 1468 |
| LMArena Multi-Turn | — | 1464 |
Frequently asked questions
Is GPT-5.3 Codex better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 45.8 on the Noometry Index.
Which is cheaper, GPT-5.3 Codex 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-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.3 Codex and MiMo-V2.6-Pro share?
2 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and MiMo-V2.6-Pro has 19.