Compare / Claude Haiku 5.5 vs GPT-5.4 mini
Claude Haiku 5.5 vs GPT-5.4 mini
Which is cheaper, which is more capable, and which does better at each kind of work, from 10 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 GPT-5.4 mini? The short answer
Pick Claude Haiku 5.5: it scores higher (Intelligence Index 43.4 against 24.1) and costs less.
- Claude Haiku 5.5 is cheaper to run: $0.002 against $0.021 per game of bullet chess on BulletBench (11 times less).
- Claude Haiku 5.5 scores higher on the Artificial Analysis Intelligence Index: 43.4 against 24.1.
- Claude Haiku 5.5 is newer: released 7 Oct 2026, against 17 Mar 2026 for GPT-5.4 mini.
- 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 | GPT-5.4 mini | |
|---|---|---|
| Price per million tokens | $0.10 in · $0.50 out | $0.75 in · $4.50 out |
| Blended (3 in : 1 out) | $0.20 | $1.69 |
| Cheapest host, blended | – | $1.69 (Azure) |
| Cost per game of bullet chess (BulletBench) | $0.002 | $0.021 |
| Cached input, per million | – | $0.075 cached input |
| Intelligence Index | 43.4 | 24.1 |
| Spring Prompt overall | 44 | – |
| Output speed, tokens a second | 235 | – |
| Context window | 1,000,000 tokens | 400,000 tokens |
| Released | 7 Oct 2026 (newer) | 17 Mar 2026 |
| Weights | Closed | Closed |
| Developer based in | the US | the US |
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 | GPT-5.4 mini |
|---|---|---|
| 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 | 56 of 164 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 19 of 198 | 71 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | not measured | 58 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 66 of 152 |
| Speed under pressureGood decisions against a real clock (fast chess) | 15 of 22 | 12 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 | GPT-5.4 mini |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better | $0.0019no reasoning | $0.0205no reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better | 310no reasoning | 197no reasoning |
| Games lost on time · Bullet 60s% of games, lower is better | 37.5%no reasoning | 50.0%no reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 43.4max reasoning | 24.1xhigh reasoning |
| Humanity's Last Exam% of questions, higher is better | 44.4%max reasoning | 28.1%xhigh reasoning |
| Terminal-Bench 4.0% of tasks, higher is better | 32.8%max reasoning | 2.0%xhigh reasoning |
Show all 10 results (4 more)
| Measure | Claude Haiku 5.5 | GPT-5.4 mini |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Bullet 60s% of moves, lower is better | 0.0%no reasoning | 0.0%no reasoning |
| Median move time · Bullet 60smilliseconds, lower is better | 1.7 sno reasoning | 0.9 sno reasoning |
| Artificial Analysis reported by Artificial Analysis · 2 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 82.7%max reasoning | 77.0%xhigh reasoning |
| SciCode% of problems, higher is better | 55.0%max reasoning | 52.1%xhigh reasoning |
Quick answers
Is Claude Haiku 5.5 better than GPT-5.4 mini?
Pick Claude Haiku 5.5: it scores higher (Intelligence Index 43.4 against 24.1) and costs less.
Which is cheaper, Claude Haiku 5.5 or GPT-5.4 mini?
Claude Haiku 5.5 is cheaper to run: $0.002 against $0.021 per game of bullet chess on BulletBench (11 times less).
Run Claude Haiku 5.5 and GPT-5.4 mini on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.