Skip to main content

Model profile

Claude Sonnet 4.5

AnthropicEstablishedReleased September 2025
Data verified
Overall Score
53.61Public #96 of 200
Arena Elo
1346
Eligible category ranks
2of 8
Price (1M tokens)
$3 in / $15 out
API pricing
Speed
Not listed
Context
200K

Evidence coverage

12 of 321 tracked benchmarks are published. 10 are verified and 2 provisional. 6 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
12 / 321
Verified
10
Provisional
2
Categories with evidence
6 / 8

Evidence by category

  • Agentic5 benchmarks
    Verified
  • Coding1 benchmark
    Verified
  • Reasoning1 benchmark
    Verified
  • Knowledge1 benchmark
    Verified
  • Math3 benchmarks
    Mixed evidence
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following0 benchmarks
    Not measured
ProprietaryNon-Reasoning
Confidence:
Medium
base

Claude Sonnet 4.5 ranks #96 out of 200 models on the public leaderboard with an overall score of 53.61/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Claude Sonnet 4.5 is a proprietary model with a 200K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

Claude Sonnet 4.5 sits inside the Claude Sonnet 4.5 family alongside Claude Sonnet 4.5 Thinking. This profile currently has 12 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Coding (#57), while its weakest is Agentic (#66). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 53.4354.06

  1. MiMo-V2-Flash
    Xiaomi
    #9154.06
    MiMo-V2-Flash is #91 with a score of 54.06.
    Compare
  2. DeepSeek V4 Flash (High)
    DeepSeek
    #9253.95
    DeepSeek V4 Flash (High) is #92 with a score of 53.95.
    Compare
  3. Qwen3.6-27B
    Alibaba
    #9353.82
    Qwen3.6-27B is #93 with a score of 53.82.
    Compare
  4. GPT-5.1
    OpenAI
    #9453.65
    GPT-5.1 is #94 with a score of 53.65.
    Compare
  5. DeepSeek V3.1
    DeepSeek
    #9553.64
    DeepSeek V3.1 is #95 with a score of 53.64.
    Compare
  6. Claude Sonnet 4.5Current model
    Anthropic
    #9653.61
    Claude Sonnet 4.5 is #96 with a score of 53.61.
  7. DeepSeek V3.1 (Reasoning)
    DeepSeek
    #9753.43
    DeepSeek V3.1 (Reasoning) is #97 with a score of 53.43.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding54%
    Eligible cohort rank #57 of 122Category score 51.6
  2. Agentic45%
    Eligible cohort rank #66 of 119Category score 46.9

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #66 of 119Percentile 45thWeight 22%5 benchmarksVerified46.9
CodingRank #57 of 122Percentile 54thWeight 20%1 benchmarkVerified51.6
ReasoningRank Not rankedWeight 17%1 benchmarkVerified29.4
KnowledgeRank Not rankedWeight 12%1 benchmarkVerified72.1
MathRank Not rankedWeight 5%3 benchmarksMixed sources35.1
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%1 benchmarkReported91.8
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1346Not availableNot available

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic5 benchmarks
Terminal-Bench 2.0Provider exact
50%Weighted 38%
Source: Anthropic: Claude Opus 4.5 system cardProvenance: Provider exact
OSWorld-VerifiedProvider exact
61.4%Weighted 34%
Source: Anthropic: Claude Opus 4.5 system cardProvenance: Provider exact
VITA-BenchBenchmark exact
17.0%Display only
Source: VitaBench leaderboardProvenance: Benchmark exact
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

48.51%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
JobBenchBenchmark exact
27.7%Display only
Source: JobBench paperProvenance: JobBench reports Sonnet-4.5 under Claude Code on the main-set leaderboard. BenchLM stores the reported main-set score.
Coding1 benchmark
SWE-bench VerifiedProvider exact

Software Engineering Benchmark Verified

77.2%Weighted 16%
Source: Anthropic: Claude Opus 4.5 system cardProvenance: Provider exact
Reasoning1 benchmark
ARC-AGI-2Provider exact

Abstraction and Reasoning Corpus for AGI v2

13.6%Weighted 31%
Source: Anthropic: Claude Opus 4.5 system cardProvenance: Provider exact
Knowledge1 benchmark
GPQAProvider exact

Graduate-Level Google-Proof Q&A

83.4%Weighted 7%
Source: Anthropic: Claude Opus 4.5 system cardProvenance: Provider exact
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

13.495%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 13.495% for claude-sonnet-4-5-20250929_59K. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

4.167%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 4.167% for claude-sonnet-4-5-20250929_32K. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
AIME 2025Reported

American Invitational Mathematics Examination 2025

87%Display only
Source: Reported upstream sourceProvenance: Reported row carried from an upstream public source. Displayable on BenchLM, but not treated as verified unless explicitly marked otherwise.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1222Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.

Claude Sonnet 4.5 Family

Base entry

Frequently Asked Questions

How does Claude Sonnet 4.5 perform overall in AI benchmarks?

Claude Sonnet 4.5 has 12 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Claude Sonnet 4.5 good for knowledge and understanding?

Claude Sonnet 4.5 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Claude Sonnet 4.5 good for coding and programming?

Claude Sonnet 4.5 ranks #57 out of 122 models in coding and programming benchmarks with an average score of 51.6. There are stronger options in this category.

Is Claude Sonnet 4.5 good for mathematics?

Claude Sonnet 4.5 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Claude Sonnet 4.5 good for reasoning and logic?

Claude Sonnet 4.5 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Claude Sonnet 4.5 good for agentic tool use and computer tasks?

Claude Sonnet 4.5 ranks #66 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 46.9. There are stronger options in this category.

Is Claude Sonnet 4.5 good for multimodal and grounded tasks?

Claude Sonnet 4.5 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to Claude Sonnet 4.5?

Claude Sonnet 4.5 belongs to the Claude Sonnet 4.5 family. Related variants on BenchLM include Claude Sonnet 4.5 Thinking.

Does Claude Sonnet 4.5 have full benchmark coverage on BenchLM?

Not yet. Claude Sonnet 4.5 currently has 12 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Claude Sonnet 4.5?

Claude Sonnet 4.5 has a published context window of 200K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.