# GPT-5.3 Codex vs MiniMax-M2.5

> GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 38.3 on the Noometry Index. MiniMax-M2.5 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.

- Canonical page: https://noometry.com/compare/gpt-5-3-codex-vs-minimax-m2-5
- Last updated: 2026-10-12
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. GPT-5.3 Codex scores higher in 2 categories and MiniMax-M2.5 in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 30.4.
- The biggest single-benchmark swing is Terminal-Bench: 78.4% for GPT-5.3 Codex and 42.7% for MiniMax-M2.5.
- MiniMax-M2.5 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-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 45.8 | 38.3 |
| Rank | 69 | 188 |
| Context | 400K | 205K |
| Input $/M | $1.75 | $0.30 |
| Output $/M | $14 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Codex: 48.6 (#56)
- MiniMax-M2.5: 48.1 (#58)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1409 | 1387 |
| ALE-Bench | 1,655 | 618.17 |
| SWE-bench Verified | 74.8% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 1381 |

## Agentic & Tool Use

- GPT-5.3 Codex: 48.0 (#9)
- MiniMax-M2.5: 30.4 (#77)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | 78.4% | 42.7% |
| Vending-Bench 2 | 5,940 | -23.16 |
| METR Time Horizons | 74.5% | — |

## Reasoning

- GPT-5.3 Codex: —
- MiniMax-M2.5: 17.5 (#292)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| Epoch Capabilities Index | 156.77 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LMArena Hard Prompts | — | 1372 |

## Math

- GPT-5.3 Codex: —
- MiniMax-M2.5: 26.9 (#253)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| ProofBench | — | 4% |
| LMArena Math | — | 1378 |

## Knowledge

- GPT-5.3 Codex: —
- MiniMax-M2.5: 39.2 (#135)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | — | 9.1% |
| LMArena Expert | — | 1379 |

## Multilingual

- GPT-5.3 Codex: —
- MiniMax-M2.5: 47.1 (#152)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | — | 1338 |
| LMArena Chinese | — | 1393 |
| LMArena French | — | 1362 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1171 |
| LMArena Korean | — | 1232 |
| LMArena Russian | — | 1358 |
| LMArena Spanish | — | 1354 |

## Instruction Following

- GPT-5.3 Codex: —
- MiniMax-M2.5: 71.5 (#148)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1353 |

## Long Context

- GPT-5.3 Codex: —
- MiniMax-M2.5: 37.5 (#216)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
| LMArena Longer Query | — | 1366 |

## Writing & Preference

- GPT-5.3 Codex: —
- MiniMax-M2.5: 53.9 (#153)

| Benchmark | GPT-5.3 Codex | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | — | 1359 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1364 |

## FAQ

### Is GPT-5.3 Codex better than MiniMax-M2.5?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 38.3 on the Noometry Index. MiniMax-M2.5 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-M2.5?

MiniMax-M2.5 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-M2.5 better for coding?

They score almost the same on coding (48.6 vs 48.1); test both on your own repository before choosing.

### 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-M2.5 share?

5 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and MiniMax-M2.5 has 33.