Model comparison
GPT-5.4 vs MiMo-V2.6-Pro
GPT-5.4 is the stronger model overall, scoring 59.5 to 46.7 on the Noometry Index. MiMo-V2.6-Pro costs 10× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GPT-5.4 scores higher in 6 categories and MiMo-V2.6-Pro in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 leads 73.3 to 37.9.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2.50 / $15 for GPT-5.4.
- GPT-5.4 accepts more context: 1.05M tokens versus 1.05M.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 59.5 | 46.7 |
| Released | 2026-03-05 | 2026-09-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $2.50 | $0.43 |
| Output $ / M tokens | $15 | $0.87 |
| Results tracked | 68 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5.4: 52.8 (#28), MiMo-V2.6-Pro: 53.2 (#27)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1465 | 1618 |
| LMArena Coding | 1497 | 1538 |
| SWE-bench Verified | 76.9% | — |
| DeepSWE | 51.8% | — |
| SciCode | 56.6% | — |
| GSO | 31.4% | — |
| WeirdML | 77.7% | — |
| MirrorCode | 15.6% | — |
| ALE-Bench | 1,607 | — |
| AlgoTune | 1.85 | — |
Agentic & Tool Use Not comparable
GPT-5.4: 46.5 (#12), MiMo-V2.6-Pro: —
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| Terminal-Bench | 81.8% | — |
| APEX-Agents | 52.4% | — |
| τ²-bench Banking | 39.4% | — |
| DeepResearch Bench | 35.1% | — |
| PostTrainBench | 19% | — |
| GBAEval | 45.1% | — |
| LMArena Search | 1197 | — |
| METR Time Horizons | 74.3% | — |
| Vending-Bench 2 | 6,144 | — |
Reasoning GPT-5.4 leads
GPT-5.4: 61.7 (#17), MiMo-V2.6-Pro: 30.4 (#76)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1511 |
| ARC-AGI-2 | 74% | — |
| Kagi LLM Benchmark | 63.8% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 93.7% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 44% | — |
| EnigmaEval | 16% | — |
| Thematic Generalization | 80% | — |
| EBR-Bench | 25.4% | — |
| Mystery Game Puzzles | 37% | — |
| DTBench | 94.4% | — |
| LMCA | 52% | — |
| Epoch Capabilities Index | 156.92 | — |
| ForecastBench | 59.5 | — |
Math GPT-5.4 leads
GPT-5.4: 73.3 (#14), MiMo-V2.6-Pro: 37.9 (#91)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1488 | 1497 |
| FrontierMath (Tiers 1-3) | 78.6% | — |
| FrontierMath Tier 4 | 49% | — |
| MathArena Final-Answer Competitions | 83.1% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
| ProofBench | 56% | — |
| FrontierMath (Feb 2025 set) | 47.6% | — |
| FrontierMath Tier 4 (v1) | 27.1% | — |
Knowledge GPT-5.4 leads
GPT-5.4: 65.3 (#13), MiMo-V2.6-Pro: 43.0 (#85)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1507 | 1548 |
| GPQA Diamond | 93.3% | — |
| Humanity's Last Exam | 36.2% | — |
| SimpleQA Verified | 45.1% | — |
| Vectara Hallucination Rate | 7% | — |
Multimodal GPT-5.4 leads
GPT-5.4: 43.8 (#19), MiMo-V2.6-Pro: 40.2 (#40)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1302 | 1265 |
| Blueprint-Bench 2 | 27.1% | — |
| Furniture Assembly | 37.5% | — |
| LMArena Document | 1471 | — |
Multilingual Too close to call
GPT-5.4: 56.4 (#22), MiMo-V2.6-Pro: 57.0 (#15)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1465 | 1474 |
| LMArena Chinese | 1520 | 1532 |
| LMArena Russian | 1480 | 1481 |
| LMArena French | 1493 | — |
| LMArena German | 1472 | — |
| LMArena Japanese | 1484 | — |
| LMArena Korean | 1449 | — |
| LMArena Spanish | 1453 | — |
Instruction Following Too close to call
GPT-5.4: 77.3 (#25), MiMo-V2.6-Pro: 78.2 (#10)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1469 | 1490 |
Long Context GPT-5.4 leads
GPT-5.4: 50.3 (#8), MiMo-V2.6-Pro: 46.0 (#26)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1474 | 1500 |
| CL-bench | 27.9% | — |
| CL-bench Life | 21.7% | — |
Writing & Preference GPT-5.4 leads
GPT-5.4: 72.1 (#18), MiMo-V2.6-Pro: 66.9 (#32)
| Benchmark | GPT-5.4 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1469 | 1491 |
| LMArena Creative Writing | 1439 | 1465 |
| LMArena Multi-Turn | 1482 | 1463 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1272 | — |
Frequently asked questions
Is GPT-5.4 better than MiMo-V2.6-Pro?
GPT-5.4 is the stronger model overall, scoring 59.5 to 46.7 on the Noometry Index. MiMo-V2.6-Pro costs 10× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 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-5.4 lists at $2.50 and $15.
Is GPT-5.4 or MiMo-V2.6-Pro better for coding?
They score almost the same on coding (52.8 vs 53.2); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.4 does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-5.4 and MiMo-V2.6-Pro share?
14 benchmarks have published results for both models. GPT-5.4 has 68 scored results on Noometry and MiMo-V2.6-Pro has 14.