Models / Claude Sonnet 4

Anthropic

Claude Sonnet 4

Claude Sonnet 4 is strongest at writing; it is not on sale through OpenRouter, so it is here for reference.

Superseded.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 · 37 results · 4 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
18.9
Artificial Analysis, at thinking reasoning; 16.6–18.9 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
22 May 2025

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 102nd of 186Claude Opus 5.5 – – –
Models from developers based in the US 58th of 93Claude Opus 5.5 – – –

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. 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 93rd of 160 available
BenchmarkClaude Sonnet 4Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 36.3% 74th of 108 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 16.7% 51st of 105 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 118th of 188 available
BenchmarkClaude Sonnet 4Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 18.9 102nd of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 10.7% 126th of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 77.7% 104th of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 68th of 170 available
BenchmarkClaude Sonnet 4Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,402 96th of 154 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 63.7 27th of 125 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 82nd of 140 available
BenchmarkClaude Sonnet 4Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 10.3% 42nd of 72 GPT-5.4 nano 3.1%
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): 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 Claude Sonnet 4, Intelligence Index 18.9. "Similar intelligence" means within 4 points or better.

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 4Claude Opus 5.5
most intelligent available today
Claude Fable 5.2
leads overall
GPT-6.1 Sol
near the top overall
GPT-6.1 Terra
near the top overall
Price per million tokens – $8.00$16.00$4.00$2.00
Tokens a second – 96–53–
Intelligence Index 18.9 57.6–51.8–
Spring Prompt overall – 82908080
Rank among available models, by use case
Product listings – 13th5th2nd4th
Decks from an analysis – 7th4th5th8th
User surveys – 4th1st3rd8th
Marketing planning – 9th1st–2nd
Agents and tool use 93rd of 160 3rd–6th7th
Professional work – 3rd–9th–
Reasoning and knowledge 118th of 188 1st–6th22nd
Writing 68th of 170 5th–16th–
Sticking to the facts 82nd of 140 3rd–20th–
Speed under pressure – –8th3rd17th

Shaded figures are better than Claude Sonnet 4's. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), mid-field on every use case measured so far.

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

Every result

37 published results from 4 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 Text: business, management and financeArena rating, higher is better 1,387
1,379–1,395
175 of 406 Claude Sonnet 4 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,381
1,372–1,389
180 of 406 Claude Sonnet 4 (thinking-32k reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,388
1,379–1,397
132 of 411 Claude Sonnet 4 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,396
1,386–1,405
113 of 411 Claude Sonnet 4 (thinking-32k reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,402
1,388–1,415
174 of 363 Claude Sonnet 4 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,433
1,418–1,447
138 of 363 Claude Sonnet 4 (thinking-32k reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,396
1,389–1,403
152 of 413 Claude Sonnet 4 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,415
1,409–1,422
117 of 413 Claude Sonnet 4 (thinking-32k reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,391
1,386–1,395
173 of 413 Claude Sonnet 4 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,402
1,397–1,406
157 of 413 Claude Sonnet 4 (thinking-32k reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,390
1,383–1,397
142 of 412 Claude Sonnet 4 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,398
1,391–1,406
130 of 412 Claude Sonnet 4 (thinking-32k 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 · 17 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 37.6 126 of 187 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 16.6 240 of 413 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 18.9 219 of 413 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 68.3% 256 of 360 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 77.7% 193 of 360 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.3% 369 of 419 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 10.7% 273 of 419 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 45.4% 166 of 288 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 54.7% 121 of 288 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 44.0% 301 of 407 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 70.3% 195 of 407 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 36.3% 128 of 188 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 27.3% 117 of 282 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 31.1% 103 of 282 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 16.7% 95 of 175 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 52.3% 161 of 286 Claude Sonnet 4 (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 64.6% 142 of 286 Claude Sonnet 4 (thinking reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 4.0% 32 of 379 Claude Sonnet 4 (no reasoning) 12 Sep 2025
UGI: requested-length error% off the requested word count, lower is better 13.0% 111 of 379 Claude Sonnet 4 (thinking reasoning) 12 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 149 of 379 Claude Sonnet 4 (no reasoning) 12 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 157 of 379 Claude Sonnet 4 (thinking reasoning) 12 Sep 2025
UGI: writing scorescore out of 100, higher is better 63.7 78 of 379 Claude Sonnet 4 (no reasoning) 12 Sep 2025
UGI: writing scorescore out of 100, higher is better 62.3 91 of 379 Claude Sonnet 4 (thinking reasoning) 12 Sep 2025

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 98.6% 76 of 108 Claude Sonnet 4 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 10.3% 60 of 108 Claude Sonnet 4 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.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.