Models / GPT-5.6 Luna

OpenAI

GPT-5.6 Luna

GPT-5.6 Luna is best for reasoning and knowledge; a strong pick at a modest price. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $0.45.

Superseded. GPT-6 Luna is OpenAI's newer model in this line, at $0.20 blended: see GPT-6 Luna or compare the two.

Results 16 Nov 2026 · 85 results · 6 sources

Test GPT-5.6 Luna on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.20 in · $1.20 out
OpenAI's list price, 10 Nov 2026 · compare prices$0.02 cached input · 50% off in batch
Speed
Not measured
Intelligence Index
37.3
Artificial Analysis, at max reasoning; 15.5–37.3 across 6 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
OpenAI, based in the US
Weights not published
Released
9 Jul 2026
1,050,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 39th of 185Claude Opus 5.5 – $0.45 blended, 34th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 5th of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.45 blended, 18th percentilecheapest: MiMo-V2.6-Flash –
Models from developers based in the US 28th of 92Claude Opus 5.5 – $0.45 blended, 25th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 58th of 159 available · 7th of 47 at its price
BenchmarkGPT-5.6 LunaRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 11.6% 39th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 80.9% 20th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 31.1% 31st of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $4,095 30th of 53 GPT-6 Astra $15,515
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 20th of 51 available · 1st of 3 at its price
BenchmarkGPT-5.6 LunaRank among availableBest available
GDP.pdfGDP.pdf: professional document tasks · reported 22.7% 15th of 31 GPT-5.6 Sol 30.7%
  • APEX-Agents: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 44th of 187 available · 5th of 61 at its price
BenchmarkGPT-5.6 LunaRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 37.3 39th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 39.5% 46th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 91.1% 29th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 60th of 169 available · 8th of 58 at its price
BenchmarkGPT-5.6 LunaRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,453 50th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 53.7 50th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 60th of 139 available · 9th of 40 at its price
BenchmarkGPT-5.6 LunaRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,460 36th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 41.0% 38th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against GPT-5.6 Luna at $0.45 blended, Intelligence Index 37.3. "Similar intelligence" means within 4 points or better.

Where to run it

6 hosts on OpenRouter at the standard service tier, with a median of $0.47 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Amazon Bedrocknot stated$0.20$1.20$0.45
Azurenot stated$0.20$1.20$0.45
OpenAInot stated$0.20$1.20$0.45
Amazon Bedrocknot stated$0.22$1.32$0.49
Azurenot stated$0.22$1.32$0.49
Azurenot stated$0.22$1.32$0.49

Other service tiers, not counted above: OpenAI fast $0.40 in, $2.40 out; OpenAI flex $0.10 in, $0.60 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

GPT-5.6 LunaMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
MiMo-V2.6-Flash
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.45 $0.54$0.18$8.00
Tokens a second – 434696
Intelligence Index 37.3 46.337.957.6
Spring Prompt overall – ––82
Rank among available models, by use case
Product listings – ––13th
Decks from an analysis – ––7th
User surveys – ––4th
Marketing planning – ––9th
Agents and tool use 58th of 159 23rd42nd3rd
Professional work 20th of 51 ––3rd
Reasoning and knowledge 44th of 187 13th55th1st
Writing 60th of 169 23rd56th5th
Sticking to the facts 60th of 139 10th46th3rd
Speed under pressure – –––

Shaded figures are better than GPT-5.6 Luna's. A dash means no result.

Research and examples

Where it has been measured

5th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the top quarter (by percentile) for reasoning and knowledge.

Artificial Analysis lists it but has not published a speed for it yet

Every result

85 published results from 6 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 12 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better -0.03
-0.05–-0.02
35 of 50 GPT-5.6 Luna (xhigh reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better -0.04
-0.06–-0.02
37 of 50 GPT-5.6 Luna (xhigh reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.00
-0.01–0.01
33 of 50 GPT-5.6 Luna (xhigh reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.00
23 of 50 GPT-5.6 Luna (xhigh reasoning, arena agent) 2 Oct 2026
Arena Document: overallArena rating, higher is better 1,462
1,454–1,470
23 of 44 GPT-5.6 Luna (xhigh reasoning) 13 Sep 2026
Arena Text factuality: overallArena rating, higher is better 1,460
1,457–1,464
47 of 182 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,463
1,455–1,471
54 of 406 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,409
1,401–1,417
93 of 411 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,491
1,482–1,501
58 of 363 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,445
1,439–1,451
74 of 413 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,453
1,449–1,457
75 of 413 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,433
1,426–1,440
76 of 412 GPT-5.6 Luna (xhigh reasoning) 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 54 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 63.3 69 of 187 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 44.2 112 of 187 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 71.4 47 of 187 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 50.7 99 of 187 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 39.3 122 of 187 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 68.6 59 of 187 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 32.1 106 of 413 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 21.0 198 of 413 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 37.3 80 of 413 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 25.0 154 of 413 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 15.5 249 of 413 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 34.6 87 of 413 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.2% 81 of 360 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 83.5% 145 of 360 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 91.1% 51 of 360 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 85.9% 115 of 360 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 64.5% 280 of 360 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.5% 75 of 360 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 33.4% 133 of 419 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 19.8% 202 of 419 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 39.5% 91 of 419 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 25.8% 175 of 419 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 7.2% 310 of 419 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 37.0% 109 of 419 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 80.3% 70 of 407 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 70.0% 199 of 407 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 83.7% 15 of 407 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 75.0% 152 of 407 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 42.7% 308 of 407 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 81.7% 50 of 407 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 51.6% 93 of 205 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 46.1% 141 of 205 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 53.6% 74 of 205 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 46.8% 138 of 205 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 40.4% 160 of 205 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 50.5% 107 of 205 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 69.7% 71 of 188 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 43.4% 119 of 188 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 80.9% 42 of 188 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 53.2% 101 of 188 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 39.0% 124 of 188 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 77.9% 55 of 188 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 2.5% 120 of 204 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 11.6% 93 of 204 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.5% 143 of 204 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 1.0% 134 of 204 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 3.5% 115 of 204 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 25.2% 75 of 175 GPT-5.6 Luna (high reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 12.8% 112 of 175 GPT-5.6 Luna (low reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 31.1% 58 of 175 GPT-5.6 Luna (max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 17.7% 92 of 175 GPT-5.6 Luna (medium reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 9.7% 126 of 175 GPT-5.6 Luna (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 28.7% 68 of 175 GPT-5.6 Luna (xhigh reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

GDP.pdf · reported by GDP.pdf · 2 results
MeasureValueRankConfigurationDated
GDP.pdf: professional document tasks% of rubric, higher is better 22.7% 21 of 49 GPT-5.6 Luna 1 Oct 2026
GDP.pdf: professional document tasks% of rubric, higher is better 22.7% 21 of 49 GPT-5.6 Luna (medium reasoning) 1 Oct 2026

Not shown: Not your documents; 100 tasks, so small differences are noise.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 41.0% 43 of 85 GPT-5.6 Luna (max reasoning) 10 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

UGI Leaderboard · reported by UGI Leaderboard · 15 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 16.0% 135 of 379 GPT-5.6 Luna (high reasoning) 9 Jul 2026
UGI: requested-length error% off the requested word count, lower is better 19.0% 171 of 379 GPT-5.6 Luna (low reasoning) 9 Jul 2026
UGI: requested-length error% off the requested word count, lower is better 20.0% 187 of 379 GPT-5.6 Luna (medium reasoning) 9 Jul 2026
UGI: requested-length error% off the requested word count, lower is better 17.0% 148 of 379 GPT-5.6 Luna (no reasoning) 9 Jul 2026
UGI: requested-length error% off the requested word count, lower is better 15.0% 127 of 379 GPT-5.6 Luna (xhigh reasoning) 9 Jul 2026
UGI: style adherencescore from 0 to 1, higher is better 0.37 89 of 379 GPT-5.6 Luna (high reasoning) 9 Jul 2026
UGI: style adherencescore from 0 to 1, higher is better 0.37 95 of 379 GPT-5.6 Luna (low reasoning) 9 Jul 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 68 of 379 GPT-5.6 Luna (medium reasoning) 9 Jul 2026
UGI: style adherencescore from 0 to 1, higher is better 0.36 145 of 379 GPT-5.6 Luna (no reasoning) 9 Jul 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 61 of 379 GPT-5.6 Luna (xhigh reasoning) 9 Jul 2026
UGI: writing scorescore out of 100, higher is better 53.7 145 of 379 GPT-5.6 Luna (high reasoning) 9 Jul 2026
UGI: writing scorescore out of 100, higher is better 47.0 179 of 379 GPT-5.6 Luna (low reasoning) 9 Jul 2026
UGI: writing scorescore out of 100, higher is better 49.2 169 of 379 GPT-5.6 Luna (medium reasoning) 9 Jul 2026
UGI: writing scorescore out of 100, higher is better 41.0 218 of 379 GPT-5.6 Luna (no reasoning) 9 Jul 2026
UGI: writing scorescore out of 100, higher is better 52.8 151 of 379 GPT-5.6 Luna (xhigh reasoning) 9 Jul 2026

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $4,095 36 of 63 GPT-5.6 Luna 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will GPT-5.6 Luna work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.