Models / Claude Opus 4.6

Anthropic

Claude Opus 4.6

Claude Opus 4.6 is best for writing, and agents and tool use; pick it when quality matters more than cost. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $10.00.

Superseded. Claude Opus 5.5 is Anthropic's newer model in this line, at $8.00 blended: see Claude Opus 5.5 or compare the two.

Results 16 Nov 2026 · 57 results · 10 sources

Test Claude Opus 4.6 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$5.00 in · $25.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
31.9
Artificial Analysis, at max reasoning; 26.4–31.9 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Anthropic, based in the US
Weights not published
Released
5 Feb 2026
1,000,000 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 49th of 185Claude Opus 5.5 – $10.00 blended, 94th percentilecheapest: Mistral Nemo –
Models priced $10 or more per million tokens 8th of 11Claude Fable 5.1 – sets this group –
Models with similar intelligence sets this group – $10.00 blended, 94th percentilecheapest: DeepSeek-V4-Flash (0731) –
Models from developers based in the US 33rd of 92Claude Opus 5.5 – $10.00 blended, 88th 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 $10 or more 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 18th of 159 available · 3rd of 9 at its price
BenchmarkClaude Opus 4.6Rank among availableBest available
OpenHands IndexOpenHands Index: average · reported 66.7% 4th of 31 Claude Fable 5 81.0%
Vending-Bench 2Vending-Bench 2: money after a year · reported $8,018 9th of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 27th of 51 available · 8th of 9 at its price
BenchmarkClaude Opus 4.6Rank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 46.3% 26th of 37 Claude Sonnet 5.5 75.5%
Remote Labor IndexRemote Labor Index: projects done to client standard · reported 4.2% 7th of 12 GPT-6 Astra 20.8%
  • GDP.pdf: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 52nd of 187 available · 8th of 11 at its price
BenchmarkClaude Opus 4.6Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 31.9 49th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 39.9% 44th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 89.6% 44th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 4th of 169 available · 2nd of 10 at its price
BenchmarkClaude Opus 4.6Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,505 2nd of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 70.9 6th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 57th of 139 available · 8th of 12 at its price
BenchmarkClaude Opus 4.6Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 12.2% 57th of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,494 4th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 47.0% 29th of 68 GPT-6 Astra 75.6%
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Claude Opus 4.6 at $10.00 blended, Intelligence Index 31.9. "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 $10.00 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Amazon Bedrocknot stated$5.00$25.00$10.00
Anthropicnot stated$5.00$25.00$10.00
Azurenot stated$5.00$25.00$10.00
Claude Platform on AWSnot stated$5.00$25.00$10.00
Googlenot stated$5.00$25.00$10.00
Googlenot stated$5.50$27.50$11.00

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.

Claude Opus 4.6Claude Fable 5.1
most intelligent at $10 or more per million tokens
DeepSeek-V4-Flash (0731)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $10.00 $20.00$0.20$8.00
Tokens a second – 72–96
Intelligence Index 31.9 53.434.357.6
Spring Prompt overall – 64–82
Rank among available models, by use case
Product listings – 24th–13th
Decks from an analysis – 11th–7th
User surveys – ––4th
Marketing planning – 10th–9th
Agents and tool use 18th of 159 19th43rd3rd
Professional work 27th of 51 4th–3rd
Reasoning and knowledge 52nd of 187 5th47th1st
Writing 4th of 169 19th–5th
Sticking to the facts 57th of 139 5th105th3rd
Speed under pressure – –––

Shaded figures are better than Claude Opus 4.6's. A dash means no result.

Research and examples

Where it has been measured

8th most intelligent of the 11 models priced $10 or more per million tokens. Among models available today, in the top quarter (by percentile) for writing, and agents and tool use.

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

Every result

57 published results from 10 sources, each in the source's own units, with the configuration that produced it.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 46.3% 27 of 39 Claude Opus 4.6 (max reasoning) 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 17 results
MeasureValueRankConfigurationDated
Arena Document: overallArena rating, higher is better 1,494
1,488–1,500
4 of 44 Claude Opus 4.6 13 Sep 2026
Arena Document: overallArena rating, higher is better 1,495
1,489–1,502
2 of 44 Claude Opus 4.6 (high reasoning) 13 Sep 2026
Arena Search: overallArena rating, higher is better 1,223
1,218–1,228
4 of 34 Claude Opus 4.6 (arena search) 24 Aug 2026
Arena Text factuality: overallArena rating, higher is better 1,488
1,486–1,491
6 of 182 Claude Opus 4.6 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,494
1,491–1,496
4 of 182 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,500
1,494–1,506
7 of 406 Claude Opus 4.6 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,501
1,495–1,507
6 of 406 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,479
1,473–1,485
12 of 411 Claude Opus 4.6 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,501
1,494–1,507
4 of 411 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,533
1,526–1,541
12 of 363 Claude Opus 4.6 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,547
1,539–1,555
3 of 363 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,499
1,494–1,504
6 of 413 Claude Opus 4.6 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,514
1,508–1,519
3 of 413 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,497
1,494–1,501
7 of 413 Claude Opus 4.6 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,505
1,501–1,508
2 of 413 Claude Opus 4.6 (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,490
1,485–1,495
8 of 412 Claude Opus 4.6 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,500
1,494–1,505
4 of 412 Claude Opus 4.6 (high reasoning) 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 14 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 31.9 107 of 413 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 26.4 142 of 413 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.6% 72 of 360 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 84.0% 139 of 360 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 39.9% 87 of 419 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 19.1% 209 of 419 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 53.1% 128 of 288 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 44.6% 170 of 288 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 78.0% 117 of 407 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 67.0% 222 of 407 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 46.2% 29 of 282 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 48.5% 25 of 282 Claude Opus 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 92.1% 46 of 286 Claude Opus 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 84.8% 81 of 286 Claude Opus 4.6 (no reasoning) 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 66.7% 4 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 41.8% 5 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 56.2% 3 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 80.0% 7 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 76.8% 6 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 78.8% 6 of 34 Claude Opus 4.6 (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Remote Labor Index · reported by Remote Labor Index · 1 result
MeasureValueRankConfigurationDated
Remote Labor Index: projects done to client standard% of projects, higher is better 4.2% 7 of 14 Claude Opus 4.6 1 Oct 2026

Not shown: Not speed or cost; a small set of projects, so a few points either way are noise.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 47.0% 32 of 85 Claude Opus 4.6 (max reasoning) 27 Aug 2026

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

tau2-bench · reported by tau2-bench · 2 results
MeasureValueRankConfigurationDated
tau2 v1.0.1, banking knowledge, alltools retrieval: consistency (pass^4)% of tasks, higher is better 11.3% 15 of 21 Claude Opus 4.6 (max reasoning, tau2) 6 May 2026
tau2 v1.0.1, banking knowledge, alltools retrieval: task success (pass^1)% of tasks, higher is better 27.3% 14 of 21 Claude Opus 4.6 (max reasoning, tau2) 6 May 2026

Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

UGI Leaderboard · reported by UGI Leaderboard · 12 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 5.0% 41 of 379 Claude Opus 4.6 (high reasoning) 6 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 4.0% 32 of 379 Claude Opus 4.6 (low reasoning) 6 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 3.0% 22 of 379 Claude Opus 4.6 (max reasoning) 6 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 4.0% 32 of 379 Claude Opus 4.6 (medium reasoning) 6 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.42 7 of 379 Claude Opus 4.6 (high reasoning) 6 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.40 30 of 379 Claude Opus 4.6 (low reasoning) 6 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.41 14 of 379 Claude Opus 4.6 (max reasoning) 6 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.41 12 of 379 Claude Opus 4.6 (medium reasoning) 6 Feb 2026
UGI: writing scorescore out of 100, higher is better 70.9 17 of 379 Claude Opus 4.6 (high reasoning) 6 Feb 2026
UGI: writing scorescore out of 100, higher is better 66.1 56 of 379 Claude Opus 4.6 (low reasoning) 6 Feb 2026
UGI: writing scorescore out of 100, higher is better 70.7 18 of 379 Claude Opus 4.6 (max reasoning) 6 Feb 2026
UGI: writing scorescore out of 100, higher is better 69.0 30 of 379 Claude Opus 4.6 (medium reasoning) 6 Feb 2026

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

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.8% 34 of 108 Claude Opus 4.6 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 12.2% 83 of 108 Claude Opus 4.6 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $8,018 9 of 63 Claude Opus 4.6 1 Oct 2026

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

Will Claude Opus 4.6 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.