Models / Claude Sonnet 5

Anthropic

Claude Sonnet 5

Claude Sonnet 5 is best for reasoning and knowledge, 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 $4.00.

Superseded.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 · 68 results · 6 sources

Test Claude Sonnet 5 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$2.00 in · $10.00 out
Anthropic's list price, 10 Nov 2026 · compare prices$0.20 cached input · 50% off in batch
Speed
Not measured
Intelligence Index
38.2
Artificial Analysis, at max reasoning; 23.2–38.2 across 6 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
30 Jun 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 36th of 185Claude Opus 5.5 – $4.00 blended, 83rd percentilecheapest: Mistral Nemo –
Models priced $3–10 per million tokens 18th of 38Claude Opus 5.5 – sets this group –
Models with similar intelligence sets this group – $4.00 blended, 75th percentilecheapest: MiMo-V2.6-Flash –
Models from developers based in the US 26th of 92Claude Opus 5.5 – $4.00 blended, 68th 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 41st of 159 available · 19th of 35 at its price
BenchmarkClaude Sonnet 5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 14.1% 32nd of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 80.5% 21st of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 37.3% 22nd of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $6,378 14th 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: has not measured this model.
  • 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 19th of 51 available · 11th of 23 at its price
BenchmarkClaude Sonnet 5Rank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 54.5% 16th of 37 Claude Sonnet 5.5 75.5%
  • 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 39th of 187 available · 22nd of 39 at its price
BenchmarkClaude Sonnet 5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 38.2 36th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 41.3% 39th 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 37th of 169 available · 16th of 34 at its price
BenchmarkClaude Sonnet 5Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,462 38th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 62.7 29th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 80th of 139 available · 23rd of 31 at its price
BenchmarkClaude Sonnet 5Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,452 46th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 33.7% 49th 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 Claude Sonnet 5 at $4.00 blended, Intelligence Index 38.2. "Similar intelligence" means within 4 points or better.

Where to run it

10 hosts on OpenRouter at the standard service tier, with a median of $4.20 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Amazon Bedrocknot stated$2.00$10.00$4.00
Anthropicnot stated$2.00$10.00$4.00
Azurenot stated$2.00$10.00$4.00
Claude Platform on AWSnot stated$2.00$10.00$4.00
Googlenot stated$2.00$10.00$4.00
Amazon Bedrocknot stated$2.20$11.00$4.40
Amazon Bedrocknot stated$2.20$11.00$4.40
Azurenot stated$2.20$11.00$4.40

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 2 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 5Claude Opus 5.5
most intelligent at $3–10 per million tokens
MiMo-V2.6-Flash
cheapest with similar intelligence
Claude Fable 5.2
leads overall
GPT-6.1 Sol
near the top overall
Price per million tokens $4.00 $8.00$0.18$16.00$4.00
Tokens a second – 9646–53
Intelligence Index 38.2 57.637.9–51.8
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 41st of 159 3rd42nd–6th
Professional work 19th of 51 3rd––9th
Reasoning and knowledge 39th of 187 1st55th–6th
Writing 37th of 169 5th56th–16th
Sticking to the facts 80th of 139 3rd46th–18th
Speed under pressure – ––8th3rd

Shaded figures are better than Claude Sonnet 5's. A dash means no result.

Research and examples

Where it has been measured

18th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for reasoning and knowledge, agents and tool use, and writing.

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

Every result

68 published results from 6 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 54.5% 17 of 39 Claude Sonnet 5 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) · 13 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better 0.01
-0.02–0.05
27 of 50 Claude Sonnet 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better 0.09
0.03–0.14
14 of 50 Claude Sonnet 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.05
0.03–0.07
14 of 50 Claude Sonnet 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.00
20 of 50 Claude Sonnet 5 (high reasoning, arena agent) 2 Oct 2026
Arena Document: overallArena rating, higher is better 1,476
1,468–1,483
15 of 44 Claude Sonnet 5 (high reasoning) 13 Sep 2026
Arena Search: overallArena rating, higher is better 1,196
1,189–1,203
12 of 34 Claude Sonnet 5 (arena search) 24 Aug 2026
Arena Text factuality: overallArena rating, higher is better 1,452
1,448–1,455
63 of 182 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,465
1,458–1,472
51 of 406 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,435
1,428–1,442
65 of 411 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,512
1,503–1,521
26 of 363 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,467
1,461–1,472
39 of 413 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,462
1,458–1,466
57 of 413 Claude Sonnet 5 (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,451
1,445–1,458
52 of 412 Claude Sonnet 5 (high 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 · 36 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 71.5 43 of 187 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 66.4 63 of 187 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 31.7 108 of 413 Claude Sonnet 5 (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 24.3 163 of 413 Claude Sonnet 5 (low reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 38.2 75 of 413 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 28.1 129 of 413 Claude Sonnet 5 (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 23.2 174 of 413 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 34.4 90 of 413 Claude Sonnet 5 (xhigh reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 91.1% 51 of 360 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 80.0% 174 of 360 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 35.7% 114 of 419 Claude Sonnet 5 (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 21.9% 191 of 419 Claude Sonnet 5 (low reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 41.3% 78 of 419 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 30.0% 148 of 419 Claude Sonnet 5 (medium reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 19.0% 211 of 419 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 39.0% 95 of 419 Claude Sonnet 5 (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 76.7% 137 of 407 Claude Sonnet 5 (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 67.3% 219 of 407 Claude Sonnet 5 (low reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 82.0% 44 of 407 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 73.7% 168 of 407 Claude Sonnet 5 (medium reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 70.0% 199 of 407 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 76.7% 137 of 407 Claude Sonnet 5 (xhigh reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 54.3% 63 of 205 Claude Sonnet 5 (high reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 50.1% 112 of 205 Claude Sonnet 5 (low reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 54.3% 63 of 205 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 51.6% 93 of 205 Claude Sonnet 5 (medium reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 54.1% 68 of 205 Claude Sonnet 5 (xhigh reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 80.5% 43 of 188 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 75.3% 63 of 188 Claude Sonnet 5 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 5.1% 110 of 204 Claude Sonnet 5 (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 2.5% 120 of 204 Claude Sonnet 5 (low reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 14.1% 81 of 204 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 2.0% 125 of 204 Claude Sonnet 5 (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 7.1% 103 of 204 Claude Sonnet 5 (xhigh reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 37.3% 41 of 175 Claude Sonnet 5 (max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 15.7% 99 of 175 Claude Sonnet 5 (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 2 results
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 33.7% 55 of 85 Claude Sonnet 5 (max reasoning) 27 Aug 2026
SimpleQA Verified: correct answers% of questions, higher is better 32.9% 58 of 85 Claude Sonnet 5 (xhigh reasoning) 27 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 3.0% 22 of 379 Claude Sonnet 5 (high reasoning) 30 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 3.0% 22 of 379 Claude Sonnet 5 (low reasoning) 30 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 6.0% 49 of 379 Claude Sonnet 5 (max reasoning) 30 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 3.0% 22 of 379 Claude Sonnet 5 (medium reasoning) 30 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 7.0% 56 of 379 Claude Sonnet 5 (xhigh reasoning) 30 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.37 95 of 379 Claude Sonnet 5 (high reasoning) 30 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 167 of 379 Claude Sonnet 5 (low reasoning) 30 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.37 112 of 379 Claude Sonnet 5 (max reasoning) 30 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 82 of 379 Claude Sonnet 5 (medium reasoning) 30 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 71 of 379 Claude Sonnet 5 (xhigh reasoning) 30 Jun 2026
UGI: writing scorescore out of 100, higher is better 56.8 125 of 379 Claude Sonnet 5 (high reasoning) 30 Jun 2026
UGI: writing scorescore out of 100, higher is better 53.0 150 of 379 Claude Sonnet 5 (low reasoning) 30 Jun 2026
UGI: writing scorescore out of 100, higher is better 62.7 87 of 379 Claude Sonnet 5 (max reasoning) 30 Jun 2026
UGI: writing scorescore out of 100, higher is better 52.4 153 of 379 Claude Sonnet 5 (medium reasoning) 30 Jun 2026
UGI: writing scorescore out of 100, higher is better 58.5 114 of 379 Claude Sonnet 5 (xhigh reasoning) 30 Jun 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 $6,378 14 of 63 Claude Sonnet 5 1 Oct 2026

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

Will Claude Sonnet 5 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.