Skip to main content

Model comparison

Claude Sonnet 4.5 Thinking vs Claude Sonnet 4.6

Data verified

Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

No comparison
65.07/100
0 category wins0 category wins

Public leaderboard positions: Claude Sonnet 4.5 Thinking unranked (Not scored); Claude Sonnet 4.6 #32 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.5 Thinking and Claude Sonnet 4.6 share 2 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to Claude Sonnet 4.5 Thinking; 31 to Claude Sonnet 4.6.

Updated July 23, 2026
Shared results
2
Claude Sonnet 4.5 Thinking only
0
Claude Sonnet 4.6 only
31
Comparable categories
0 / 8

Benchmark data for Claude Sonnet 4.5 Thinking and Claude Sonnet 4.6 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Sonnet 4.5 Thinking and Claude Sonnet 4.6
CategoryClaude Sonnet 4.5 ThinkingΔClaude Sonnet 4.6
AgenticClaude Sonnet 4.5 ThinkingNot measuredMarginNo overlapClaude Sonnet 4.665.2
CodingClaude Sonnet 4.5 ThinkingNot measuredMarginNo overlapClaude Sonnet 4.669.1
KnowledgeClaude Sonnet 4.5 ThinkingNot measuredMarginNo overlapClaude Sonnet 4.666.0
MathClaude Sonnet 4.5 ThinkingNot measuredMarginNo overlapClaude Sonnet 4.626.4
MultimodalClaude Sonnet 4.5 ThinkingNot measuredMarginNo overlapClaude Sonnet 4.677.4

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Comparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.5 ThinkingNot availableClaude Sonnet 4.6$3 input / $15 outputA complete price comparison is not available.
Generation speedtokens per secondClaude Sonnet 4.5 ThinkingNot availableClaude Sonnet 4.644 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 4.5 ThinkingNot availableClaude Sonnet 4.61.48 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 4.5 Thinking200KClaude Sonnet 4.6200KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
Terminal-Bench 2.0Source 59.1%Not comparable
OSWorld-VerifiedSource 72.1%Not comparable
Claw-EvalSource 67.8%Not comparable
CyberGymSource 65.2%Not comparable
τ²-bench resultsSource 79.5%Not comparable
Gert LabsSource 62.92%Not comparable
OSWorld 2.0Source 8.3%Not comparable
JobBenchSource 36.9%Not comparable
Coding
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
Vibe Code BenchSource 22.62%51.48%Claude Sonnet 4.6 leads
SWE-bench VerifiedSource 79.6%Not comparable
SWE-RebenchSource 60.7%Not comparable
React Native EvalsSource 80.6%Not comparable
cursorBench31Source 48.8%Not comparable
AA-SciCodeSource 46.9%Not comparable
FrontierCode 1.1 MainSource 24.3%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
AA-LCRSource 57.7%Not comparable
CritPtSource 0.9%Not comparable
Knowledge
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
GPQASource 89.9%Not comparable
SuperGPQASource 95%Not comparable
MMLU-ProSource 79.2%Not comparable
HLESource 49%Not comparable
Artificial Analysis Intelligence IndexSource 35.9%Not comparable
AA-GPQA DiamondSource 79.9%Not comparable
AA-HLESource 13.2%Not comparable
AA-Omniscience IndexSource -2.9%Not comparable
AA-Omniscience AccuracySource 38.0%Not comparable
AA-Omniscience Hallucination RateSource 65.9%Not comparable
Math
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
FrontierMath v2 (Tiers 1-3)Source 32.400%Not comparable
FrontierMath v2 (Tier 4)Source 8.300%Not comparable
Multimodal
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
Design Arena WebsiteSource 12191314Claude Sonnet 4.6 leads
CharXivSource 77.4%Not comparable
AA-MMMU-ProSource 70.6%Not comparable
Inst. Following
BenchmarkClaude Sonnet 4.5 ThinkingClaude Sonnet 4.6Result
AA-IFBenchSource 41.2%Not comparable
Frequently Asked Questions (3)

Can I compare Claude Sonnet 4.5 Thinking and Claude Sonnet 4.6 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Claude Sonnet 4.5 Thinking and Claude Sonnet 4.6 today?

Claude Sonnet 4.6: $3.00 input / $15.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.