Skip to main content

Model comparison

Claude Haiku 4.5 vs GPT-5.6 Luna

Data verified

Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.58/100
Margin
10.6pts
winning →
67.17/100
1 category wins1 category wins

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 scores and score margins for Claude Haiku 4.5 and GPT-5.6 Luna
CategoryClaude Haiku 4.5ΔGPT-5.6 Luna
MathClaude Haiku 4.54.9Margin 68.7GPT-5.6 Luna73.6
CodingClaude Haiku 4.573.3Margin 10.6GPT-5.6 Luna62.7
AgenticClaude Haiku 4.5Not measuredMarginNo overlapGPT-5.6 Luna84.1
KnowledgeClaude Haiku 4.5Not measuredMarginNo overlapGPT-5.6 Luna92.3
MultimodalClaude Haiku 4.5Not measuredMarginNo overlapGPT-5.6 Luna78.4

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Haiku 4.5B · GPT-5.6 Luna
  1. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 5.903%B 78.600%
    Winner: GPT-5.6 LunaΔ 72.7
    FrontierMath 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.
  2. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 2.083%B 58.500%
    Winner: GPT-5.6 LunaΔ 56.4
    FrontierMath 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.

MetricClaude Haiku 4.5GPT-5.6 LunaComparison
Input / output priceUSD per 1M tokensClaude Haiku 4.5$1 input / $5 outputGPT-5.6 Luna$1 input / $6 outputClaude Haiku 4.5 has the lower combined listed price.
Generation speedtokens per secondClaude Haiku 4.5Not availableGPT-5.6 LunaNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Haiku 4.5Not availableGPT-5.6 LunaNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Haiku 4.5200KGPT-5.6 Luna1MGPT-5.6 Luna lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
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 1584Not 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 wins
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
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
Reasoning
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
ARC-AGI-3Source 0.2%Not comparable
AA-LCRSource 74.0%Not comparable
CritPtSource 20.6%Not comparable
Knowledge
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
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 wins
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
FrontierMath v2 (Tiers 1-3)Source 5.903%78.600%GPT-5.6 Luna leads
FrontierMath v2 (Tier 4)Source 2.083%58.500%GPT-5.6 Luna leads
FrontierMath (legacy)Source 78.6%Not comparable
Multimodal
BenchmarkClaude Haiku 4.5GPT-5.6 LunaResult
Design Arena WebsiteSource 1152Not comparable
MMMU-ProSource 78.4%Not comparable
MMMU-Pro w/ PythonSource 79.5%Not comparable
AA-MMMU-ProSource 78.6%Not comparable
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

Last updated: July 23, 2026

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.