Claude Haiku 5.5 vs GPT-5.6 Luna.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | Claude Haiku 5.5 | GPT-5.6 Luna | Winner |
|---|---|---|---|
| League Score | 66.2 | 66.7 | GPT-5.6 Luna |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | — | 92.3 | — |
| Context (tokens) | 1000000 | 1050000 | GPT-5.6 Luna |
| Speed (tok/s) | — | — | — |
| Price (blended $/1M) | $0.20 | $0.45 | Claude Haiku 5.5 (cheaper) |
Tale of the tape
| Spec | Claude Haiku 5.5 | GPT-5.6 Luna |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Released | Oct 7, 2026 | Jul 9, 2026 |
| League Score | 66 | 67 |
| Context | 1,000,000 tokens | 1,050,000 tokens |
| Max output | 128,000 | 128,000 |
| $/1M input | $0.10 | $0.20 |
| $/1M output | $0.50 | $1.20 |
| Weights | Closed | Closed |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna |
|---|---|---|
| LiveBench overall | 69.8 | 66.1 |
Cost at three workloads
| Workload | Claude Haiku 5.5 | GPT-5.6 Luna |
|---|---|---|
| Light — 1M in / 250K out | $0.23 | $0.50 |
| Standard — 10M in / 2.5M out | $2.25 | $5.00 |
| Long-context — 50M in / 5M out | $7.50 | $16.00 |
The pick
Pick Claude Haiku 5.5 if you want the lower running cost.
Pick GPT-5.6 Luna if you want the higher overall League Score; you need the bigger context window.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, Claude Haiku 5.5 or GPT-5.6 Luna?
On overall League Score they are effectively tied — Claude Haiku 5.5 scores 66 and GPT-5.6 Luna scores 67. The category verdicts on this page are where the real differences live.
Which is cheaper, Claude Haiku 5.5 or GPT-5.6 Luna?
Claude Haiku 5.5 is cheaper: $0.20 vs $0.45 blended per 1M tokens (3:1 input/output mix) — about 2.2x less per token.
Which has the bigger context window, Claude Haiku 5.5 or GPT-5.6 Luna?
GPT-5.6 Luna, with 1.1M of context against 1M for Claude Haiku 5.5.
Are Claude Haiku 5.5 and GPT-5.6 Luna open source?
Claude Haiku 5.5 is closed weights — API access only; GPT-5.6 Luna is closed weights — API access only.