Claude Haiku 5.5 Benchmarks: Should GPT-6 Luna Be Worried?
Anthropic has released Claude Haiku 5.5, its fastest Claude model, with a 1M-token context window and prices starting at $0.10 per million input tokens. Here are all the Claude Haiku 5.5 benchmarks compared with Haiku 4.5, GPT-6 Luna, and Sonnet 5.5, plus pricing and specs.
Haiku 5.5 vs other models
| Benchmark | Claude Haiku 5.5 | Claude Haiku 4.5 | GPT-6 Luna | Claude Sonnet 5.5 |
|---|---|---|---|---|
| GDPval-AA v2.1 | 1620 | 735 | 1437 | 1840 |
| AA-Briefcase v1.1 | 1578 | 614 | 1336 | 1824 |
| OSWorld 2.1 | 72.4% | 15.7% | 48.9% | 83.9% |
| Humanity's Last Exam, no tools | 45.9% | 10.2% | - | 56.9% |
| Humanity's Last Exam, with tools | 57.4% | 18.7% | - | 64.5% |
| Terminal-Bench 4.0 | 39.2% | 0.0% | 16.4% | 70.6% |
| FrontierCode 1.1 (Main) | 46.4% | - | 42.4% | 52.1%Xhigh effort |
| Chartography, no tools | 46.4% | 6.4% | 29.1% | 61.6% |
A dash means no score has been reported for that model.
Benchmarks: Haiku 4.5 vs Haiku 5.5
| Benchmark | Claude Haiku 5.5 | Claude Haiku 4.5 | Improvement |
|---|---|---|---|
| GDPval-AA v2.1 | 1620 | 735 | +885 |
| AA-Briefcase v1.1 | 1578 | 614 | +964 |
| OSWorld 2.1 | 72.4% | 15.7% | +56.7 points |
| Humanity's Last Exam, no tools | 45.9% | 10.2% | +35.7 points |
| Humanity's Last Exam, with tools | 57.4% | 18.7% | +38.7 points |
| Terminal-Bench 4.0 | 39.2% | 0.0% | +39.2 points |
| Chartography, no tools | 46.4% | 6.4% | +40.0 points |
API pricing
| Model | Input, per 1M tokens | Cache read | Cache write | Output, per 1M tokens |
|---|---|---|---|---|
| Claude Haiku 5.5, prompts up to 100K | $0.10 | $0.01 | $0.125 | $0.50 |
| Claude Haiku 5.5, prompts over 100K | $0.50 | $0.05 | $0.625 | $2.50 |
| Claude Haiku 4.5 | $1 | $0.10 | $1.25 | $5 |
| Claude Sonnet 5.5 | $2 | $0.10 | $2.50 | $10 |
| Claude Opus 5.5 | $4 | - | - | $20 |
| Claude Fable 5.1 | $10 | - | - | $50 |
Haiku 5.5 vs Sonnet 5.5 pricing
| Model | Input, per 1M tokens | Output, per 1M tokens | Input vs Sonnet 5.5 | Output vs Sonnet 5.5 |
|---|---|---|---|---|
| Claude Haiku 5.5, prompts up to 100K | $0.10 | $0.50 | 20x cheaper | 20x cheaper |
| Claude Haiku 5.5, prompts over 100K | $0.50 | $2.50 | 4x cheaper | 4x cheaper |
| Claude Sonnet 5.5 | $2 | $10 | - | - |
Specs
| Specification | Claude Haiku 5.5 | Claude Haiku 4.5 |
|---|---|---|
| Context window | 1M tokens | 200K tokens |
| Max output | 128K tokens | 64K tokens |
| Batch max output | 300K tokens | - |
| Knowledge cutoff | June 2026 | - |
| Adaptive thinking | Yes | No |
| Adjustable effort | Yes | No |
| Default effort | Medium | - |
| Image input | Yes | Yes |
| Browser use | Yes | - |
| Speed | Fastest Claude model | - |
| API model ID | claude-haiku-5-5 | claude-haiku-4-5 |
| Released | October 7, 2026 | - |