← comparisons · head to head
Mistral Large 4 vs Claude Sonnet 5.5
Claude Sonnet 5.5 scores higher than Mistral Large 4 on all 5 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Mistral Large 4 is at 20.9 and Claude Sonnet 5.5 at 83.3 (out of 100). On each maker's API, Mistral Large 4 costs $0.70 / $2.10 per 1M tokens (input / output) and Claude Sonnet 5.5 $2 / $10.
Scores as published by each board; table composed November 13, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Mistral Large 4 | Claude Sonnet 5.5 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,564.5 | 1,772.3 | Claude Sonnet 5.5 |
| LiveBench global average (0-100) | 40.9 | 77 | Claude Sonnet 5.5 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 56.5 | 70.9 | Claude Sonnet 5.5 |
| Artificial Analysis intelligence index · measured runs only | 26.1 | 54.5 | Claude Sonnet 5.5 |
| Epoch AI Epoch Capabilities Index (ECI) · many benchmarks on one scale | 154.6 | 166.6 | Claude Sonnet 5.5 |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Mistral Large 4 is at 14 (#46 of 48) and Claude Sonnet 5.5 at 65.1 (#16). Claude Sonnet 5.5 scores higher on all 3 coding boards that rate both.
| Coding board | Mistral Large 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena · Coding | 1,457.5 | 1,500.9 |
| LiveBench · Coding | 44.4 | 77.2 |
| Vals Vibe Code Bench | 81.6 | 92.4 |
Mistral Large 4 at a glance
- Developer
- Mistral
- Status
- Live since October 6, 2026
- API price
- $0.70 input / $2.10 output per 1M tokens · Mistral, mistral-large-4
- Context window
- 1.05M tokens
Live — Oct 6, public preview on Mistral's API and OpenRouter · 1T total / 49B active · open weights since Oct 29 on Hugging Face (Mistral Ecosystem Open-Weight License, a modified MIT; running it as a paid API service needs a separate license), an improved checkpoint after three more weeks of RL by Mistral's account · $0.70 / $2.10 per 1M from Oct 29 ($0.07 cached, Mistral's docs) · Artificial Analysis Intelligence Index v5.0: 26 (read Oct 29) · Epoch Capabilities Index (read Oct 15): 146.9, 71st of 277, level with OpenAI's o3 from April 2025 (146.9) and behind the open-weight Kimi K3 (157.4), GLM-5.3 (155.9) and DeepSeek V4 Pro (155.3).
Mistral Large 4's weights are out, and Mistral says they beat its own preview
2026-10-29 · Mistral published the weights of Mistral Large 4 on Hugging Face on October 29, two days inside the end-of-October date it gave when the model went to public preview on October 6. The repository, mistralai/Mistral-Large-4-1T-A52B, holds the full checkpoint in 54 shards and is not gated.
Mistral Large 4 is out in public preview: 1T parameters, $0.68 in and $2.09 out for now, open weights by the end of October
2026-10-06 · Mistral launched Mistral Large 4 today as a public preview on its own API. Per Mistral's docs it is a natively multimodal mixture-of-experts model with about 1.05 trillion total parameters and 49 billion active, plus a 1.6B vision encoder. Mistral says it will release the open weights by the end of this month.
Claude Sonnet 5.5 at a glance
- Developer
- Anthropic
- Status
- Live since September 28, 2026
- API price
- $2 input / $10 output per 1M tokens · Anthropic, claude-sonnet-5-5
- Context window
- 1M tokens
Live — Sep 28 · $2/$10 per MTok, the same as Sonnet 5 · cache reads $0.20 at launch, halved to $0.10 on Oct 7, writes $2.50 · in the API, the Claude apps, AWS, Google Cloud and Azure the same day · 1M ctx / 128K out · knowledge cutoff Jun 2026 · Artificial Analysis Intelligence Index 56 at max effort, #3 of 216 reasoning models (read Sep 28) · Anthropic's own table: Terminal-Bench 4.0 70.6% (Opus 5.5 66.4%), OSWorld 2.1 80.1% (Opus 5.5 81.8%) · our sweep caught claude-sonnet-5-5 at 17:54 UTC and fired at 17:55.
Claude Sonnet 5.5 ships at Sonnet 5's price, and the first independent number puts it #3 among reasoning models
2026-09-28 · Claude Sonnet 5.5 is live. Our sweep read the id claude-sonnet-5-5 at 17:54:45 UTC on September 28 and the alert went out at 17:55:45, 60 seconds later, to 314 inboxes and one phone. OpenRouter listed it nine minutes after that.
Claude Sonnet 5.5: named by Anthropic, reportedly in partner testing, priced 89% by Sep 30
2026-09-27 · Anthropic has named Claude Sonnet 5.5 but has not dated it. Everything past the name is reported, not confirmed - and the one number that moves every day says it is close.
Mistral Large 4 vs Claude Sonnet 5.5: quick answers
Which is better, Mistral Large 4 or Claude Sonnet 5.5?
It depends on what you measure. Claude Sonnet 5.5 scores higher than Mistral Large 4 on all 5 public leaderboards that rate both. Claude Sonnet 5.5's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Mistral Large 4 is at 20.9 and Claude Sonnet 5.5 at 83.3 (out of 100).
Which is newer, Mistral Large 4 or Claude Sonnet 5.5?
Mistral Large 4. It went live on October 6, 2026, 8 days after Claude Sonnet 5.5 (September 28, 2026).
Which is cheaper, Mistral Large 4 or Claude Sonnet 5.5?
Mistral Large 4 is cheaper on both input and output. On each vendor's own API, Mistral Large 4 is $0.70 input / $2.10 output per million tokens and Claude Sonnet 5.5 is $2 input / $10 output per million tokens. Prices as published in the models.dev catalog, as of 2026-11-12.
Which has the bigger context window, Mistral Large 4 or Claude Sonnet 5.5?
Mistral Large 4, at 1.05M tokens against Claude Sonnet 5.5's 1M, as each vendor lists it.
How do Mistral Large 4 and Claude Sonnet 5.5 compare for coding?
On the ArtificialWatch coding index, Mistral Large 4 is at 14 (#46 of 48) and Claude Sonnet 5.5 at 65.1 (#16). Claude Sonnet 5.5 scores higher on all 3 coding boards that rate both.
Who makes Mistral Large 4 and Claude Sonnet 5.5?
Mistral Large 4 is from Mistral; Claude Sonnet 5.5 is from Anthropic.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed November 13, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear when the next one drops. Free.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · what a workload costs on each · the wire