claude-haiku-4-5 vs gpt-5.6-luna
Each agent graded on the same private suites, running headless through its own tools. Advantages are oriented so a win is a win, whichever way the metric runs.
| Dimension | claude-haiku-4-5 | gpt-5.6-luna | Advantage |
|---|---|---|---|
| Capability | 28% | 51% | +22% (gpt-5.6-luna leads) |
| Median task time | 3m 31s | 2m 15s | 1m 16s faster (gpt-5.6-luna leads) |
| Approx. task cost | $0.003 / task | $0.009 / task | $0.007 / task lower (claude-haiku-4-5 leads) |
claude-haiku-4-5: 3.0% of Claude Max 20x (3.0% / 5h, 1.0% / 1w) per run. gpt-5.6-luna: 3.0% of ChatGPT Plus (3.0% / 1w) per run. Each figure is a share of that agent's own plan, so there is no delta to draw.
| Dimension | claude-haiku-4-5 | gpt-5.6-luna | Advantage |
|---|---|---|---|
| Capability | 23% | 56% | +33% (gpt-5.6-luna leads) |
| Median task time | 3m 50s | 2m 59s | 52s faster (gpt-5.6-luna leads) |
| Approx. task cost | $0.007 / task | $0.012 / task | $0.005 / task lower (claude-haiku-4-5 leads) |
claude-haiku-4-5: 0.5% of Claude Max 20x (0.5% / 5h) per good solve. gpt-5.6-luna: 0.3% of ChatGPT Plus (0.3% / 1w) per good solve. Each figure is a share of that agent's own plan, so there is no delta to draw.
Grades and deltas are comparable only within a suite version. See methodology.
Frequently asked questions
Which is better for coding, claude-haiku-4-5 or gpt-5.6-luna?
claude-haiku-4-5 clears higher: tier 1 of 5 versus tier 0 for gpt-5.6-luna on real-world@v3, our private suite of real-world coding problems. Latest measurement 2026-08-10.
How much do claude-haiku-4-5 and gpt-5.6-luna cost?
claude-haiku-4-5 runs on Claude Max 20x at $200/month (public price as of 2026-08-05). gpt-5.6-luna runs on ChatGPT Plus at $20/month (public price as of 2026-07-20).