Models / Claude Sonnet 4.6

Anthropic

Claude Sonnet 4.6

Claude Sonnet 4.6 is best for writing; 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 $6.00.

Superseded. Claude Sonnet 5.5 is Anthropic's newer model in this line, at $4.00 blended: see Claude Sonnet 5.5 or compare the two.

Results 16 Nov 2026 · 53 results · 9 sources

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

Price per million tokens
$3.00 in · $15.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
30.1
Artificial Analysis, at max reasoning; 24.7–30.1 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
17 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 53rd of 185Claude Opus 5.5 – $6.00 blended, 90th percentilecheapest: Mistral Nemo –
Models priced $3–10 per million tokens 23rd of 38Claude Opus 5.5 – sets this group –
Models with similar intelligence sets this group – $6.00 blended, 92nd percentilecheapest: Nemotron 3.5 Super VL –
Models from developers based in the US 35th of 92Claude Opus 5.5 – $6.00 blended, 81st 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 $3–10 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 60th of 159 available · 26th of 35 at its price
BenchmarkClaude Sonnet 4.6Rank among availableBest available
OpenHands IndexOpenHands Index: average · reported 44.5% 22nd of 31 Claude Fable 5 81.0%
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 3.0% 49th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 71.2% 35th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 34.4% 27th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $7,204 12th 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.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 31st of 51 available · 16th of 23 at its price
BenchmarkClaude Sonnet 4.6Rank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 43.0% 28th of 37 Claude Sonnet 5.5 75.5%
GDP.pdfGDP.pdf: professional document tasks · reported 18.0% 18th of 31 GPT-5.6 Sol 30.7%
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 66th of 187 available · 26th of 39 at its price
BenchmarkClaude Sonnet 4.6Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 30.1 53rd of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 33.6% 68th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 87.5% 55th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 32nd of 169 available · 13th of 34 at its price
BenchmarkClaude Sonnet 4.6Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,472 31st of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 64.6 24th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 75th of 139 available · 22nd of 31 at its price
BenchmarkClaude Sonnet 4.6Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 10.6% 46th of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,461 35th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 35.5% 44th 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 Sonnet 4.6 at $6.00 blended, Intelligence Index 30.1. "Similar intelligence" means within 4 points or better.

Where to run it

9 hosts on OpenRouter at the standard service tier, with a median of $6.00 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Amazon Bedrocknot stated$3.00$15.00$6.00
Anthropicnot stated$3.00$15.00$6.00
Azurenot stated$3.00$15.00$6.00
Claude Platform on AWSnot stated$3.00$15.00$6.00
Googlenot stated$3.00$15.00$6.00
Amazon Bedrocknot stated$3.30$16.50$6.60
Amazon Bedrocknot stated$3.30$16.50$6.60
Googlenot stated$3.30$16.50$6.60

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 1 dearer hosts are left out.

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 Sonnet 4.6Claude Opus 5.5
most intelligent at $3–10 per million tokens
Nemotron 3.5 Super VL
cheapest with similar intelligence
Claude Fable 5.2
leads overall
GPT-6.1 Sol
near the top overall
Price per million tokens $6.00 $8.00$0.24$16.00$4.00
Tokens a second – 96411–53
Intelligence Index 30.1 57.626.5–51.8
Spring Prompt overall – 82–9080
Rank among available models, by use case
Product listings – 13th–5th2nd
Decks from an analysis – 7th–4th5th
User surveys – 4th–1st3rd
Marketing planning – 9th–1st–
Agents and tool use 60th of 159 3rd132nd–6th
Professional work 31st of 51 3rd––9th
Reasoning and knowledge 66th of 187 1st74th–6th
Writing 32nd of 169 5th––16th
Sticking to the facts 75th of 139 3rd––18th
Speed under pressure – ––8th3rd

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

Where it has been measured

23rd most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for writing.

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

Every result

53 published results from 9 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 43.0% 30 of 39 Claude Sonnet 4.6 (high 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) · 9 results
MeasureValueRankConfigurationDated
Arena Document: overallArena rating, higher is better 1,478
1,472–1,484
13 of 44 Claude Sonnet 4.6 13 Sep 2026
Arena Search: overallArena rating, higher is better 1,201
1,196–1,206
10 of 34 Claude Sonnet 4.6 (arena search) 24 Aug 2026
Arena Text factuality: overallArena rating, higher is better 1,461
1,458–1,464
46 of 182 Claude Sonnet 4.6 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,482
1,475–1,488
24 of 406 Claude Sonnet 4.6 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,449
1,443–1,456
38 of 411 Claude Sonnet 4.6 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,506
1,498–1,514
33 of 363 Claude Sonnet 4.6 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,474
1,469–1,480
28 of 413 Claude Sonnet 4.6 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,472
1,469–1,476
43 of 413 Claude Sonnet 4.6 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,455
1,449–1,461
44 of 412 Claude Sonnet 4.6 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 · 19 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 63.0 70 of 187 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 30.1 115 of 413 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 24.7 159 of 413 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 87.5% 98 of 360 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 79.9% 176 of 360 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 33.6% 131 of 419 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 13.3% 248 of 419 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 56.6% 115 of 288 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 41.2% 199 of 288 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 80.0% 77 of 407 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 68.3% 213 of 407 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 50.1% 112 of 205 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 71.2% 70 of 188 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 3.0% 116 of 204 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 53.0% 17 of 282 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 46.2% 29 of 282 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 34.4% 50 of 175 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 75.7% 111 of 286 Claude Sonnet 4.6 (max reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 79.5% 103 of 286 Claude Sonnet 4.6 (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

GDP.pdf · reported by GDP.pdf · 1 result
MeasureValueRankConfigurationDated
GDP.pdf: professional document tasks% of rubric, higher is better 18.0% 26 of 49 Claude Sonnet 4.6 (max reasoning) 1 Oct 2026

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

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 44.5% 23 of 34 Claude Sonnet 4.6 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 30.9% 20 of 34 Claude Sonnet 4.6 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 50.0% 6 of 34 Claude Sonnet 4.6 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 13.3% 32 of 34 Claude Sonnet 4.6 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 74.4% 16 of 34 Claude Sonnet 4.6 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 54.0% 24 of 34 Claude Sonnet 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.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 2 results
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 35.5% 49 of 85 Claude Sonnet 4.6 (high reasoning) 10 Aug 2026
SimpleQA Verified: correct answers% of questions, higher is better 32.8% 59 of 85 Claude Sonnet 4.6 (max reasoning) 27 Aug 2026

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

UGI Leaderboard · reported by UGI Leaderboard · 12 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 3.0% 22 of 379 Claude Sonnet 4.6 (high reasoning) 18 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Sonnet 4.6 (low reasoning) 18 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Sonnet 4.6 (max reasoning) 18 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Sonnet 4.6 (medium reasoning) 18 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.39 35 of 379 Claude Sonnet 4.6 (high reasoning) 18 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.39 39 of 379 Claude Sonnet 4.6 (low reasoning) 18 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.41 9 of 379 Claude Sonnet 4.6 (max reasoning) 18 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.41 9 of 379 Claude Sonnet 4.6 (medium reasoning) 18 Feb 2026
UGI: writing scorescore out of 100, higher is better 64.6 71 of 379 Claude Sonnet 4.6 (high reasoning) 18 Feb 2026
UGI: writing scorescore out of 100, higher is better 59.3 108 of 379 Claude Sonnet 4.6 (low reasoning) 18 Feb 2026
UGI: writing scorescore out of 100, higher is better 64.2 76 of 379 Claude Sonnet 4.6 (max reasoning) 18 Feb 2026
UGI: writing scorescore out of 100, higher is better 61.2 95 of 379 Claude Sonnet 4.6 (medium reasoning) 18 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 99.9% 19 of 108 Claude Sonnet 4.6 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 10.6% 65 of 108 Claude Sonnet 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 $7,204 12 of 63 Claude Sonnet 4.6 1 Oct 2026

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

Will Claude Sonnet 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.