Mistral Large vs o1
Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Mistral Large has the edge where output tokens cost 10.0x less, and where what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 42
- Mistral Large only
- 2
- o1 only
- 26
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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
Intelligence
AA Intelligence Index
o1
o1 leads, 15.2 against 5.8.
Same board, both measured
Reasoning
GPQA Diamond
o1
o1 leads, 73.2% against 47.7%.
Same board, both measured
Math
AIME
o1
o1 leads, 71.5% against 9.2%.
Same board, both measured
Knowledge
MMLU Pro
o1
o1 leads, 83.5% against 69.7%.
Same board, both measured
Long documents
Listed context window
o1
o1 takes 200K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Large
Mistral Large $0.0050, o1 $0.045 per turn.
List prices
At a glance
- Coding index
- Mistral Large not benchmarked, o1 not benchmarked.
- Widest category
- Math, 24.7 points apart on average over 5 shared benchmarks.
- Widest single gap
- AIME: Mistral Large 9.2% against o1 71.5%, 62.3 points apart on a 0 to 100 scale.
- Output price
- Mistral Large $6.00 against o1 $60.00 per million output tokens, 10.0x apart.
- Context window
- Mistral Large takes 128K tokens, o1 200K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Mistral Large | Bars | o1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 5 | ||
| Knowledge | 0 | 8 | ||
| General | 0 | 17 | ||
| All shared boards | 0 | 42 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 61.7% | Only o1 measured |
| AA Coding Index | Not measured | 39.7 | Only o1 measured |
| LiveCodeBench (Vals AI) | 37.1% | 50.3% | o1 |
| LiveCodeBench (Artificial Analysis run) | 17.8% | 67.9% | o1 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 12.9% | Only o1 measured |
| WeirdML | Not measured | 46.1% | Only o1 measured |
| LMArena Text: coding | 1275 | 1367 | o1 |
| LMArena Text: software and IT | 1274 | 1366 | o1 |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.8 | 15.2 | o1 |
| Epoch Capabilities Index | 122.1 | 141.7 | o1 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 62.6% | Only o1 measured |
| METR time horizons | Not measured | 51.1% | Only o1 measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| GPQA Diamond | 47.7% | 73.2% | o1 |
| MMMU Pro (Vals AI) | Not measured | 77.4% | Only o1 measured |
| GPQA Diamond (Artificial Analysis run) | 35.1% | 74.7% | o1 |
| Humanity's Last Exam (Artificial Analysis run) | 3.5% | 7.0% | o1 |
| GPQA Diamond (Epoch AI run) | Not measured | 76.8% | Only o1 measured |
| ARC-AGI | Not measured | 30.7% | Only o1 measured |
| SimpleBench | Not measured | 40.1% | Only o1 measured |
| Chess puzzles | Not measured | 10.0% | Only o1 measured |
| VPCT | Not measured | 37.0% | Only o1 measured |
| LMArena Text: hard prompts | 1257 | 1371 | o1 |
| LMArena Text: expert | 1208 | 1361 | o1 |
| LMArena Text: hard prompts in English | 1268 | 1372 | o1 |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| AIME | 9.2% | 71.5% | o1 |
| MATH 500 (Vals AI) | 74.4% | 90.4% | o1 |
| MGSM (Vals AI) | 87.2% | 89.3% | o1 |
| OTIS Mock AIME | Not measured | 73.3% | Only o1 measured |
| FrontierMath, tiers 1 to 3 | Not measured | 14.7% | Only o1 measured |
| MATH level 5 | Not measured | 94.7% | Only o1 measured |
| LMArena Text: math | 1261 | 1388 | o1 |
| LMArena Text: mathematical work | 1257 | 1390 | o1 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| MMLU Pro | 69.7% | 83.5% | o1 |
| LegalBench (Vals AI) | Not measured | 80.4% | Only o1 measured |
| TaxEval (Vals AI) | 63.8% | 74.3% | o1 |
| MedQA (Vals AI) | 76.2% | 96.5% | o1 |
| MMLU Pro (Artificial Analysis run) | 51.5% | 84.1% | o1 |
| SimpleQA Verified | Not measured | 41.1% | Only o1 measured |
| MMLU | 68.8% | Not measured | Only Mistral Large measured |
| GeoBench | Not measured | 80.0% | Only o1 measured |
| LMArena Text: science | 1260 | 1369 | o1 |
| LMArena Text: medicine and healthcare | 1255 | 1355 | o1 |
| LMArena Text: legal and government | 1275 | 1368 | o1 |
| LMArena Text: business and finance | 1238 | 1328 | o1 |
| Neither model has a result on the other 5 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| IFBench | Not measured | 70.3% | Only o1 measured |
| Long context reasoning (AA-LCR) | Not measured | 65.0% | Only o1 measured |
| DTBench | 60.8% | 74.7% | o1 |
| LMCA | Not measured | 22.3% | Only o1 measured |
| Fiction.LiveBench | Not measured | 83.3% | Only o1 measured |
| Creative writing (Lech Mazur) | Not measured | 70.2% | Only o1 measured |
| LMArena Text | 1265 | 1366 | o1 |
| LMArena Text: instruction following | 1249 | 1367 | o1 |
| LMArena Text: creative writing | 1242 | 1347 | o1 |
| LMArena Vision | Not measured | 1168 | Only o1 measured |
| LMArena Text: English | 1284 | 1372 | o1 |
| LMArena Text: non-English | 1235 | 1358 | o1 |
| LMArena Text: Chinese | 1239 | 1394 | o1 |
| LMArena Text: German | 1242 | 1337 | o1 |
| LMArena Text: Japanese | 1170 | 1346 | o1 |
| LMArena Text: Korean | 1202 | 1396 | o1 |
| LMArena Text: French | 1325 | 1344 | o1 |
| LMArena Text: Spanish | 1268 | 1345 | o1 |
| LMArena Text: Russian | 1252 | 1356 | o1 |
| LMArena Text: Polish | 1157 | Not measured | Only Mistral Large measured |
| LMArena Text: multi-turn | 1260 | 1355 | o1 |
| LMArena Text: longer queries | 1261 | 1378 | o1 |
| LMArena Text: writing and language | 1261 | 1360 | o1 |
| LMArena Text: entertainment and media | 1230 | 1358 | o1 |
| LMArena Vision: English | Not measured | 1162 | Only o1 measured |
| LMArena Vision: Chinese | Not measured | 1235 | Only o1 measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large | o1 | Leader |
|---|---|---|---|
| Neither model has a result on 5 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 Large costs less
Repository review
50K input + 3K output tokens
Mistral Large costs less
Agent loop
200K input + 10K output tokens
Mistral Large 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 | Mistral Large | OpenAI o1 |
|---|---|---|
| Maker | Mistral AI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | February 26, 2024 | December 17, 2024 |
| Context window | 128K | 200K |
| Input $/Mtok | $2.00 | $15.00 |
| Output $/Mtok | $6.00 | $60.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Large better than o1 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Mistral Large has the edge where output tokens cost 10.0x less, and where what matters is LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, Mistral Large or o1?
Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Large or o1?
o1, with 200K tokens against 128K.
How many benchmarks is the Mistral Large vs o1 comparison based on?
42 benchmarks have a result for both models as of October 21, 2026. Mistral Large's coding index rests on 0 independent benchmarks and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.