Claude Sonnet 4.5 vs GPT-5.6 Luna
At a Glance
| Compare | Claude Sonnet 4.5Anthropic |  GPT-5.6 LunaOpenAI |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #36 of 4627.7 score · 2/3 sources · provisional · missing LiveBench · full-core range 18.5–51.8 | #31 of 4652.7 score · 3/3 sources · complete |
| CostLower is better · Published-token output estimate | UnrankedNot in the 44-model eligible cohort | #6 of 44$0.026 per LiveBench case |
| EfficiencyHigher is better · MM Efficiency v1.5 | UnrankedNot in the 38-model eligible cohort | #4 of 3864.8 score · 3/3 sources · complete |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $3.00Anthropic ↗ · Sep 3, 2026 | $0.20Openai ↗ · Sep 3, 2026 |
| Output priceFrom · USD / 1M tokens | $15.00Anthropic ↗ · Sep 3, 2026 | $1.20Openai ↗ · Sep 3, 2026 |
| Context windowMaximum documented tokens | 200K | 1,050K |
| Model facts checked | Sep 3, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | Claude Sonnet 4.5 | GPT-5.6 Luna |
|---|---|---|
| ARC-AGI-1verified-v1-ba05d69f6453 · verified_score · leader | 63.6770% of row best · percent · Claude Sonnet 4.5 (Thinking 32K) | 90.67100% of row best · percent · GPT-5.6 Luna 2026-07-30 (Max) |
| ARC-AGI-2verified-v2-6c676fa3e9af · verified_score · leader | 13.6123% of row best · percent · Claude Sonnet 4.5 (Thinking 32K) | 59.58100% of row best · percent · GPT-5.6 Luna 2026-07-30 (Max) |
| LMArena Document Arenadocument-2026-09-13-d25aabda0010 · arena_rating · statistical tie | 1,449.81100% of row best · rating · claude-sonnet-4-5-20250929; 95% CI [1443.68972646, 1455.92640287]; votes 31455; rank 28 | 1,456.92100% of row best · rating · gpt-5.6-luna-xhigh; 95% CI [1448.72029252, 1465.11301394]; votes 5766; rank 23 |
| LMArena Text Arenatext-2026-09-13-d25aabda0010 · arena_rating · statistical tie | 1,433.94100% of row best · rating · claude-sonnet-4-5-20250929-high-32k; 95% CI [1431.13982742, 1436.74901697]; votes 80980; rank 81 | 1,429.89100% of row best · rating · gpt-5.6-luna-xhigh; 95% CI [1425.11549148, 1434.66063238]; votes 28547; rank 86 |
| ToneBench2026-09-11-10-task-4ef099199c9c · overall_score · unverified | 77.2591% of row best · points · Claude Sonnet 4.5 · 7,415 output tokens / case | 84.47100% of row best · points · GPT-5.6 Luna (ultra) · 17,605 output tokens / case |
| Overall ResultCounted from the protocol-matched rows above · 2 ties | 0 benchmark winsNo overall winner | 2 benchmark winsNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | Claude Sonnet 4.5 | GPT-5.6 Luna |
|---|---|---|
| Developer | Anthropic | OpenAI |
| Family | Claude 4 | Gpt 5 6 |
| Model | Claude Sonnet 4.5 | GPT-5.6 Luna |
| Version | Claude Sonnet 4.5 | GPT-5.6 Luna |
| Lifecycle | active | active |
| Released | 2025-09-29 | Unknown |
| Knowledge cutoff | 2025-01-01 | 2026-02-16 |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 200K | 1,050K |
| Total parameters | Unknown | Unknown |
| Active parameters | Unknown | Unknown |
| License | Unknown | Unknown |
| Open weights | No | No |
| API available | Yes | Yes |
| Self-hostable | No | No |
| Provider access | Anthropic (Standard) | Openai (Standard), Openrouter (Standard) |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | chat, generation, reasoning, tools |
Claude Sonnet 4.5 Capabilities
GPT-5.6 Luna Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
Claude Sonnet 4.5Anthropic | vs | GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5.1Anthropic | vs | Claude Sonnet 4.5Anthropic | family variantsimage, text |
Claude Sonnet 4.5Anthropic | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
Claude Sonnet 4.5Anthropic | vs |  DeepSeek-V4.1-FlashDeepSeek | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs | Grok 4.6xAI | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs |  Kimi-K3Moonshot AI | cross-developer peersimage, text |
 MiniMax-M3MiniMax | vs | Claude Sonnet 4.5Anthropic | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Claude Sonnet 4.5Anthropic | vs |  Hy4 previewTencent | cross-developer peerstext |
Claude Sonnet 4.5Anthropic | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Claude Sonnet 4.5 vs GPT-5.6 Luna FAQs
Is Claude Sonnet 4.5 or GPT-5.6 Luna better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Claude Sonnet 4.5 and GPT-5.6 Luna, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Claude Sonnet 4.5 or GPT-5.6 Luna?+
Claude Sonnet 4.5 is $3.00 and GPT-5.6 Luna is $0.20 per million tokens, so GPT-5.6 Luna is cheaper on this metric. Claude Sonnet 4.5 is $15.00 and GPT-5.6 Luna is $1.20 per million tokens, so GPT-5.6 Luna is cheaper on this metric.
Which has a larger context window, Claude Sonnet 4.5 or GPT-5.6 Luna?+
GPT-5.6 Luna has the larger sourced context window. Claude Sonnet 4.5 supports 200K and GPT-5.6 Luna supports 1,050K.
Which performs better in benchmarks, Claude Sonnet 4.5 or GPT-5.6 Luna?+
There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.
Can Claude Sonnet 4.5 or GPT-5.6 Luna be self-hosted?+
Both models have the same recorded self-hosting status: unsupported. Claude Sonnet 4.5 is not marked open weight; GPT-5.6 Luna is not marked open weight.
Can Claude Sonnet 4.5 and GPT-5.6 Luna understand images?+
Claude Sonnet 4.5 is documented with image input; GPT-5.6 Luna is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Claude Sonnet 4.5 or GPT-5.6 Luna?+
GPT-5.6 Luna has the larger sourced maximum output: Claude Sonnet 4.5 supports 64K and GPT-5.6 Luna supports 128K output tokens.
Do Claude Sonnet 4.5 and GPT-5.6 Luna support reasoning and tool use?+
Claude Sonnet 4.5: reasoning, tool calling, and image input. GPT-5.6 Luna: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Claude Sonnet 4.5 or GPT-5.6 Luna?+
Claude Sonnet 4.5 has 1 sourced provider route; GPT-5.6 Luna has 2, so GPT-5.6 Luna has broader tracked availability.
Which offers better value, Claude Sonnet 4.5 or GPT-5.6 Luna?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.