Model comparison
Claude Haiku 4.5 vs GPT-5.6 Luna
Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Haiku 4.5 #77 (Estimated); GPT-5.6 Luna #22 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Haiku 4.5 and GPT-5.6 Luna share 2 comparable benchmark results. 2 of 8 categories are comparable. 3 results are unique to Claude Haiku 4.5; 39 to GPT-5.6 Luna.
Updated July 23, 2026- Shared results
- 2
- Claude Haiku 4.5 only
- 3
- GPT-5.6 Luna only
- 39
- Comparable categories
- 2 / 8
Pick GPT-5.6 Luna if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if coding is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.6 Luna is clearly ahead on the BenchAlign aggregate, 67.17 to 56.58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.6 Luna's sharpest advantage is in mathematics, where it averages 73.6 against 4.9. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 5.903% to 78.600%. Claude Haiku 4.5 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-5.6 Luna is also the more expensive model on tokens at $1.00 input / $6.00 output per 1M tokens, versus $1.00 input / $5.00 output per 1M tokens for Claude Haiku 4.5. GPT-5.6 Luna is the reasoning model in the pair, while Claude Haiku 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.6 Luna gives you the larger context window at 1M, compared with 200K for Claude Haiku 4.5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Haiku 4.5 | Δ | GPT-5.6 Luna |
|---|---|---|---|
| Math | Claude Haiku 4.54.9 | Margin→ 68.7 | GPT-5.6 Luna73.6 |
| Coding | Claude Haiku 4.573.3 | Margin← 10.6 | GPT-5.6 Luna62.7 |
| Agentic | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.6 Luna84.1 |
| Knowledge | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.6 Luna92.3 |
| Multimodal | Claude Haiku 4.5Not measured | MarginNo overlap | GPT-5.6 Luna78.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 5.903%B 78.600%Winner: GPT-5.6 LunaΔ 72.7FrontierMath v2 (Tiers 1-3): Claude Haiku 4.5 scored 5.903%; GPT-5.6 Luna scored 78.600%. GPT-5.6 Luna wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 2.083%B 58.500%Winner: GPT-5.6 LunaΔ 56.4FrontierMath v2 (Tier 4): Claude Haiku 4.5 scored 2.083%; GPT-5.6 Luna scored 58.500%. GPT-5.6 Luna wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Haiku 4.5 | GPT-5.6 Luna | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Haiku 4.5$1 input / $5 output | GPT-5.6 Luna$1 input / $6 output | Claude Haiku 4.5 has the lower combined listed price. |
| Generation speedtokens per second | Claude Haiku 4.5Not available | GPT-5.6 LunaNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Haiku 4.5Not available | GPT-5.6 LunaNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Haiku 4.5200K | GPT-5.6 Luna1M | GPT-5.6 Luna lists the larger context window. |
Benchmark Deep Dive
Agentic16 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.6 Luna | Result |
|---|---|---|---|
| JobBenchSource | 16.0% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 84.7% | Not comparable |
| BrowseCompSource | — | 83.3% | Not comparable |
| OSWorld 2.0Source | — | 45.6% | Not comparable |
| CyberGymSource | — | 77.9% | Not comparable |
| ExploitGymSource | — | 12.4% | Not comparable |
| ToolathlonSource | — | 53.4% | Not comparable |
| AA Agentic IndexSource | — | 45.6% | Not comparable |
| GDPval-AASource | — | 54.2% | Not comparable |
| GDPval-AASource | — | 1584 | Not comparable |
| AA Harvey LABSource | — | 87.9% | Not comparable |
| AA ITBenchSource | — | 40.3% | Not comparable |
| AA Tau3 BankingSource | — | 27.2% | Not comparable |
| AA AutomationBenchSource | — | 42.2% | Not comparable |
| aaTerminalBench21Source | — | 80.9% | Not comparable |
| APEX-Agents-AASource | — | 35.8% | Not comparable |
CodingClaude Haiku 4.5 wins8 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.6 Luna | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.3% | — | Not comparable |
| SWE-bench ProSource | — | 62.7% | Not comparable |
| Terminal-Bench 2.0Source | — | 84.7% | Not comparable |
| deepSweSource | — | 67.2% | Not comparable |
| FrontierCode 1.1 ExtendedSource | — | 55.1% | Not comparable |
| cursorBench32Source | — | 61.1% | Not comparable |
| AA Coding IndexSource | — | 71.5% | Not comparable |
| AA-SciCodeSource | — | 52.5% | Not comparable |
Reasoning3 benchmarks
Knowledge10 benchmarks
| Benchmark | Claude Haiku 4.5 | GPT-5.6 Luna | Result |
|---|---|---|---|
| GPQASource | — | 92.3% | Not comparable |
| GPQA-DSource | — | 92.3% | Not comparable |
| HealthBench ProfessionalSource | — | 55.7% | Not comparable |
| HealthBench HardSource | — | 32.0% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 51.2% | Not comparable |
| AA-GPQA DiamondSource | — | 91.1% | Not comparable |
| AA-HLESource | — | 37.2% | Not comparable |
| AA-Omniscience IndexSource | — | -11.2% | Not comparable |
| AA-Omniscience AccuracySource | — | 41.5% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 90.1% | Not comparable |
MathGPT-5.6 Luna wins3 benchmarks
Frequently Asked Questions (3)
Which is better, Claude Haiku 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna is ahead on BenchLM's BenchAlign leaderboard, 67.17 to 56.58. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 5.903% and 78.600%.
Which is better for coding, Claude Haiku 4.5 or GPT-5.6 Luna?
Claude Haiku 4.5 has the edge for coding in this comparison, averaging 73.3 versus 62.7. GPT-5.6 Luna stays close enough that the answer can still flip depending on your workload.
Which is better for math, Claude Haiku 4.5 or GPT-5.6 Luna?
GPT-5.6 Luna has the edge for math in this comparison, averaging 73.6 versus 4.9. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.