Model comparison
GPT-5.3 Codex vs MiniMax-M2.7
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 9.2× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
MiniMaxSummary
- They share 5 benchmarks with published results for both. GPT-5.3 Codex scores higher in 2 categories and MiniMax-M2.7 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 25.1.
- The biggest single-benchmark swing is WeirdML: 79.3% for GPT-5.3 Codex and 37% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | MiniMax-M2.7 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 45.8 | 37.7 |
| Released | 2026-02-05 | 2026-03-18 |
| Weights | Proprietary | Open |
| Context window | 400K | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.75 | $0.30 |
| Output $ / M tokens | $14 | $1.20 |
| Results tracked | 8 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-5.3 Codex: 48.6 (#56), MiniMax-M2.7: 41.8 (#120)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1409 | 1398 |
| WeirdML | 79.3% | 37% |
| ALE-Bench | 1,655 | 599.25 |
| SWE-bench Verified | 74.8% | — |
| SciCode | — | 47% |
| LMArena Coding | — | 1454 |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-5.3 Codex: 48.0 (#9), MiniMax-M2.7: 25.1 (#111)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | 78.4% | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 19.7 (#253)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| Epoch Capabilities Index | 156.77 | 145.85 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LMArena Hard Prompts | — | 1422 |
Math Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 25.9 (#263)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | — | 1420 |
Knowledge Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 37.7 (#152)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1444 |
Multilingual Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 50.3 (#123)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1441 |
| LMArena French | — | 1421 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |
Instruction Following Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 74.1 (#103)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | — | 1405 |
Long Context Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 43.3 (#99)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | — | 1419 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, MiniMax-M2.7: 58.9 (#112)
| Benchmark | GPT-5.3 Codex | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | — | 1405 |
| LMArena Creative Writing | — | 1354 |
| LMArena Multi-Turn | — | 1412 |
Frequently asked questions
Is GPT-5.3 Codex better than MiniMax-M2.7?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 9.2× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5.3 Codex or MiniMax-M2.7?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or MiniMax-M2.7 better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.3 Codex does, with 400K tokens against 205K.
How many benchmarks do GPT-5.3 Codex and MiniMax-M2.7 share?
5 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and MiniMax-M2.7 has 30.