GPT-5.1-Codex-Max vs Mistral Small 3.1 24B
Mistral Small 3.1 24B costs 18.0x less per output token than GPT-5.1-Codex-Max ($0.555 vs $10.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $10.00
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.555
GPT-5.1-Codex-Max or Mistral Small 3.1 24B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-5.1-Codex-Max for a larger context window (400K against 128K tokens).
No benchmark has tested both yet. GPT-5.1-Codex-Max has results on LiveCodeBench (Vals AI), Vibe Code Bench (Vals AI) and Terminal-Bench; Mistral Small 3.1 24B on LMArena Text: coding, LMArena Text: software and IT and LMArena Text: hard prompts. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Long documents
Listed context window
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max takes 400K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 3.1 24B
GPT-5.1-Codex-Max $0.0063, Mistral Small 3.1 24B $0.0006 per turn.
List prices
At a glance
- Coding index
- GPT-5.1-Codex-Max not benchmarked, Mistral Small 3.1 24B not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GPT-5.1-Codex-Max $10.00 against Mistral Small 3.1 24B $0.555 per million output tokens, 18.0x apart.
- Context window
- GPT-5.1-Codex-Max takes 400K tokens, Mistral Small 3.1 24B 128K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 83.6% | Not measured | Only GPT-5.1-Codex-Max measured |
| Vibe Code Bench (Vals AI) | 22.2% | Not measured | Only GPT-5.1-Codex-Max measured |
| Terminal-Bench | 60.4% | Not measured | Only GPT-5.1-Codex-Max measured |
| ALE-Bench | 1228.3 | Not measured | Only GPT-5.1-Codex-Max measured |
| LMArena Text: coding | Not measured | 1309 | Only Mistral Small 3.1 24B measured |
| LMArena Text: software and IT | Not measured | 1301 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 33 boards here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| METR time horizons | 70.8% | Not measured | Only GPT-5.1-Codex-Max measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| LMArena Text: hard prompts | Not measured | 1278 | Only Mistral Small 3.1 24B measured |
| LMArena Text: expert | Not measured | 1257 | Only Mistral Small 3.1 24B measured |
| LMArena Text: hard prompts in English | Not measured | 1290 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: diagrams | Not measured | 1119 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: homework | Not measured | 1158 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| ProofBench | 9.0% | Not measured | Only GPT-5.1-Codex-Max measured |
| LMArena Text: math | Not measured | 1261 | Only Mistral Small 3.1 24B measured |
| LMArena Text: mathematical work | Not measured | 1271 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| LMArena Text: science | Not measured | 1265 | Only Mistral Small 3.1 24B measured |
| LMArena Text: medicine and healthcare | Not measured | 1267 | Only Mistral Small 3.1 24B measured |
| LMArena Text: legal and government | Not measured | 1271 | Only Mistral Small 3.1 24B measured |
| LMArena Text: business and finance | Not measured | 1257 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 14 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index25 boards measured
| Benchmark | GPT-5.1-Codex-Max | Mistral Small 3.1 24B | Leader |
|---|---|---|---|
| LMArena Text | Not measured | 1277 | Only Mistral Small 3.1 24B measured |
| LMArena Text: instruction following | Not measured | 1263 | Only Mistral Small 3.1 24B measured |
| LMArena Text: creative writing | Not measured | 1252 | Only Mistral Small 3.1 24B measured |
| LMArena Vision | Not measured | 1136 | Only Mistral Small 3.1 24B measured |
| LMArena Text: English | Not measured | 1295 | Only Mistral Small 3.1 24B measured |
| LMArena Text: non-English | Not measured | 1255 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Chinese | Not measured | 1253 | Only Mistral Small 3.1 24B measured |
| LMArena Text: German | Not measured | 1266 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Japanese | Not measured | 1208 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Korean | Not measured | 1207 | Only Mistral Small 3.1 24B measured |
| LMArena Text: French | Not measured | 1273 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Spanish | Not measured | 1284 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Russian | Not measured | 1263 | Only Mistral Small 3.1 24B measured |
| LMArena Text: Polish | Not measured | 1242 | Only Mistral Small 3.1 24B measured |
| LMArena Text: multi-turn | Not measured | 1270 | Only Mistral Small 3.1 24B measured |
| LMArena Text: longer queries | Not measured | 1299 | Only Mistral Small 3.1 24B measured |
| LMArena Text: writing and language | Not measured | 1268 | Only Mistral Small 3.1 24B measured |
| LMArena Text: entertainment and media | Not measured | 1250 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: English | Not measured | 1157 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: Chinese | Not measured | 1155 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: reading text | Not measured | 1132 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: humor | Not measured | 1142 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: captioning | Not measured | 1153 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: recognizing things | Not measured | 1155 | Only Mistral Small 3.1 24B measured |
| LMArena Vision: creative writing | Not measured | 1123 | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 21 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mistral Small 3.1 24B costs less
Repository review
50K input + 3K output tokens
Mistral Small 3.1 24B costs less
Agent loop
200K input + 10K output tokens
Mistral Small 3.1 24B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.1-Codex-Max | Mistral Small 3.1 24B |
|---|---|---|
| Maker | OpenAI | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | December 4, 2025 | March 17, 2025 |
| Context window | 400K | 128K |
| Input $/Mtok | $1.25 | $0.351 |
| Output $/Mtok | $10.00 | $0.555 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.1-Codex-Max better than Mistral Small 3.1 24B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5.1-Codex-Max for a larger context window (400K against 128K tokens).
Which is cheaper, GPT-5.1-Codex-Max or Mistral Small 3.1 24B?
GPT-5.1-Codex-Max costs $1.25 per million input tokens and $10.00 per million output tokens; Mistral Small 3.1 24B costs $0.351 and $0.555. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-5.1-Codex-Max or Mistral Small 3.1 24B?
GPT-5.1-Codex-Max, with 400K tokens against 128K.
Has any benchmark tested both GPT-5.1-Codex-Max and Mistral Small 3.1 24B?
No benchmark has tested both yet. GPT-5.1-Codex-Max has results on LiveCodeBench (Vals AI), Vibe Code Bench (Vals AI) and Terminal-Bench; Mistral Small 3.1 24B on LMArena Text: coding, LMArena Text: software and IT and LMArena Text: hard prompts. Compare them on price and context instead. Data as of October 21, 2026.