Mistral Large 4
MistralOpen weightsModified MITReleased Oct 29, 2026
On the arena.ai Agents leaderboard, Mistral Large 4 has a Net Improvement of -5.44% (—, rank #44, 95% interval -7.47%–-3.41%). Mistral Large 4 ranks #134 on the LMArena Text leaderboard (style control) with an Arena score of 1420.4 (±8.5, 6,423 votes). Artificial Analysis Intelligence Index: 26.1. API price: $0.70 input / $2.10 output per 1M tokens. Context: 1.05M. Nearest rivals: Claude Haiku 5.5 (1421.2) above and Inkling 2 Small (1411.8) below.
Quick answer
- Agents leaderboard
- #44 of 56 · -5.44% success
- Text (LMArena)
- #134 · 1420.4
- 17NAS overall
- #43 of 55
- API price (in / out)
- $0.70 / $2.10 per 1M tokens
- Closest rival
- Claude Haiku 5.5 · 1421.2
- Cheaper alternative
- MiMo V2.5: Text 1433.6, output $0.22 (89% cheaper)
- Data updated
- Nov 15, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| highUsed in table | 26.1 | 33.4 | 95 | 1.9 | 23 |
| medium | 23.1 | 30.9 | 100 | 2.0 | 22 |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 71 |  GLM-4.6 | 1424.5 | – | $2.20 | 40 |
| 72 |  Qwen3 Max | 1423.3 | – | – | – |
| 73 |  Claude Haiku 5.5 | 1421.2 | 36.5 | $0.50 | 235 |
| 74 | Mistral Large 4This page | 1420.4 | 26.1 | $2.10 | 95 |
| 75 | TInkling 2 Small | 1411.8 | 30.6 | $1.00 | 103 |
| 76 | TInkling Small | 1405.4 | 12.9 | $1.20 | 199 |
| 77 | USolar Pro 4 | 1387.5 | 14.2 | $1.20 | 79 |
More from Mistral
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 69 | Mistral Medium 3.5 | 1426.4 | 4.6 | $7.50 | 173 |
| – | Mistral Large | – | – | $12.00 | – |
Pricing
- Official API list price: $0.70 input and $2.10 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $1.05 per 1M tokens.
- Among 95 models with an output price, it is the #29 cheapest.
- The cheapest OpenRouter route charges $0.70 input / $2.10 output.
Sources & methodology
On the arena.ai Agents leaderboard, Mistral Large 4 has a Net Improvement of -5.44% (—, rank #44, 95% interval -7.47%–-3.41%).
- arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does Mistral Large 4 do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Mistral Large 4 has a Net Improvement of -5.44% (—, rank #44, 95% interval -7.47%–-3.41%).
What rank is Mistral Large 4 right now?
Mistral Large 4 is #74 on our leaderboard of 80 scored models (Arena score 1420.4); its raw LMArena rank is #134.
What does Mistral Large 4 cost via API?
Input $0.70 / output $2.10 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $1.05 per 1M tokens.
How fast is Mistral Large 4?
Artificial Analysis measures about 95 output tokens per second, 1.9 s to the first token and 23 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is Mistral Large 4 to the models ranked next to it?
It is 0.8 points behind Claude Haiku 5.5 (1421.2) and 8.6 points ahead of Inkling 2 Small (1411.8); gaps smaller than the confidence interval (±8.5) are not significant.
Is Mistral Large 4 open source? Can it be self-hosted?
Mistral Large 4 is an open-weights model (license: Modified MIT); you can download the weights and self-host.
What is the context length of Mistral Large 4?
1.05M (1,048,576 tokens, as listed on OpenRouter).
Mistral Large 4 vs Claude Haiku 5.5: which is better?
On the LMArena Text leaderboard Mistral Large 4 scores 1420.4 and Claude Haiku 5.5 scores 1421.2 (a 0.8-point gap, within the confidence interval, so not significant). Agent task success: Mistral Large 4 -5.44%, Claude Haiku 5.5 0.47%. On price, Mistral Large 4 costs $2.10 and Claude Haiku 5.5 $0.50 per 1M output tokens.
Is there a cheaper model close to Mistral Large 4?
Yes: MiMo V2.5 scores 1433.6 on the Text leaderboard (Mistral Large 4: 1420.4) and costs $0.22 per 1M output tokens, about 89% less than Mistral Large 4 ($2.10).
Where does the Mistral Large 4 data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 15, 2026.