Compare / Claude Haiku 5.5 vs Mistral Small 4
Claude Haiku 5.5 vs Mistral Small 4
Which is cheaper, which is more capable, and which does better at each kind of work, from 12 results on 2 sources that measured both models.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
Claude Haiku 5.5 or Mistral Small 4? The short answer
Pick Claude Haiku 5.5: it scores higher (Intelligence Index 43.4 against 11.3) and costs less.
- Claude Haiku 5.5 is cheaper to run: $0.002 against $0.004 per game of bullet chess on BulletBench (2.0 times less).
- Claude Haiku 5.5 scores higher on the Artificial Analysis Intelligence Index: 43.4 against 11.3.
- Claude Haiku 5.5 writes faster: 235 tokens a second against 164.
- Claude Haiku 5.5 is newer: released 7 Oct 2026, against 16 Mar 2026 for Mistral Small 4.
- On third-party benchmarks, on the results both models have: Claude Haiku 5.5 does better for agents and tool use and reasoning and knowledge.
At a glance
| Claude Haiku 5.5 | Mistral Small 4 | |
|---|---|---|
| Price per million tokens | $0.10 in · $0.50 out | $0.15 in · $0.60 out |
| Blended (3 in : 1 out) | $0.20 | $0.26 |
| Cheapest host, blended | – | $0.26 (Mistral) |
| Cost per game of bullet chess (BulletBench) | $0.002 | $0.004 |
| Cached input, per million | – | $0.015 cached input |
| Intelligence Index | 43.4 | 11.3 |
| Spring Prompt overall | 44 | – |
| Output speed, tokens a second | 235 | 164 |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Released | 7 Oct 2026 (newer) | 16 Mar 2026 |
| Weights | Closed | Open |
| Developer based in | the US | France |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Claude Haiku 5.5 | Mistral Small 4 |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 11 of 20 | not measured |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | 10 of 19 | not measured |
| User surveysPlanning a user survey and reading its results without being misled | 3 of 8 | not measured |
| Marketing planningPlanning a year of ad spend without overspending | 17 of 19 | not measured |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 20 of 164 | 132 of 164 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 19 of 198 | 131 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | not measured | 116 of 188 |
| Speed under pressureGood decisions against a real clock (fast chess) | 15 of 22 | 9 of 22 |
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Claude Haiku 5.5 | Mistral Small 4 |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better | $0.0019no reasoning | $0.0039no reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better | 310no reasoning | 367no reasoning |
| Games lost on time · Bullet 60s% of games, lower is better | 37.5%no reasoning | 25.0%no reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 43.4max reasoning | 11.3 |
| Humanity's Last Exam% of questions, higher is better | 44.4%max reasoning | 9.9% |
| Terminal-Bench 4.0% of tasks, higher is better | 32.8%max reasoning | 0.0% |
Show all 12 results (6 more)
| Measure | Claude Haiku 5.5 | Mistral Small 4 |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Bullet 60s% of moves, lower is better | 0.0%no reasoning | 0.6%no reasoning |
| Median move time · Bullet 60smilliseconds, lower is better | 1.7 sno reasoning | 0.6 sno reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 82.7%max reasoning | 49.7% |
| Output speedtokens per second, higher is better | 235max reasoning | 164 |
| SciCode% of problems, higher is better | 55.0%max reasoning | 38.8% |
| Time to first answer tokenseconds, lower is better | 5.08low reasoning | 0.47no reasoning |
Quick answers
Is Claude Haiku 5.5 better than Mistral Small 4?
Pick Claude Haiku 5.5: it scores higher (Intelligence Index 43.4 against 11.3) and costs less.
Which is cheaper, Claude Haiku 5.5 or Mistral Small 4?
Claude Haiku 5.5 is cheaper to run: $0.002 against $0.004 per game of bullet chess on BulletBench (2.0 times less).
Which is faster, Claude Haiku 5.5 or Mistral Small 4?
Claude Haiku 5.5 writes about 235 tokens a second on its usual API, against 164 for Mistral Small 4 (Artificial Analysis).
Run Claude Haiku 5.5 and Mistral Small 4 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.