Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
13
distinct benchmarks
13
latest retrieval
2026-09-29
Change model selection
Specifications
General specifications
Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.
Specifications for Claude Opus 4.5 and Claude Sonnet 4.5
The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
API pricing for Claude Opus 4.5 and Claude Sonnet 4.5
Key to the marks:better valuebetter, but not conclusivetie
Pricing by provider
Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.
Provider pricing for Claude Opus 4.5 and Claude Sonnet 4.5
Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.
Capability profile from matched benchmarks
Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.
Claude Opus 4.5
Claude Sonnet 4.5
Coding: 100 / 80 (1 benchmark family)
Reasoning: 100 / 73.7 (1 benchmark family)
Finance: 100 / 99.2 (1 benchmark family)
Agentic tasks: 99 / 97.3 (2 benchmark families)
Multimodal: 95.2 / 100 (1 benchmark family)
Productivity: 100 / 93.8 (1 benchmark family)
Health: 99.2 / 94.9 (2 benchmark families)
Education: 100 / 84.4 (2 benchmark families)
11 matched rows from 11 benchmark families were considered. The radar shows 8 of 8 comparable categories.
Claude Opus 4.5Claude Sonnet 4.5
Agent Poker BenchOverall. Higher is better. No documented setup difference
Claude Opus 4.51,033.379 rating points
Claude Sonnet 4.5Winner1,055.504 rating points
BFCL v4Overall. Higher is better. No documented setup difference
Claude Opus 4.5Winner77.47 %
Claude Sonnet 4.573.24 %
CORE-Bench HardAutomatic validation. Higher is better. No documented setup difference
Claude Opus 4.5Winner77.78 %
Claude Sonnet 4.562.22 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Opus 4.5Winner61.305 %
Claude Sonnet 4.560.8 %
MedCodeOverall. Higher is better. No documented setup difference
Claude Opus 4.5Winner45.174 %
Claude Sonnet 4.540.569 %
MedScribeOverall. Higher is better. No documented setup difference
Claude Opus 4.583.246 %
Claude Sonnet 4.5Winner84.515 %
MultiChallengeOverall. Higher is better. No documented setup difference
Claude Opus 4.5Winner58.97% ± 0.42
Claude Sonnet 4.555.32% ± 1.47
MultiNRCOverall. Higher is better. No documented setup difference
Claude Opus 4.5Winner48.63% ± 3.02
Claude Sonnet 4.535.83% ± 2.89
PRBench FinanceOverall. Higher is better. Test setup not documented as identical
Claude Opus 4.5Higher measured value46.16% ± 0.27
Claude Sonnet 4.543.79% ± 0.4
PRBench LegalOverall. Higher is better. Test setup not documented as identical
Claude Opus 4.5Higher measured value44.21% ± 0.34
Claude Sonnet 4.540.84% ± 0.4
SAGEOverall. Higher is better. No documented setup difference
Claude Opus 4.5Winner45.002 %
Claude Sonnet 4.532.88 %
TutorBenchOverall. Higher is better. No documented setup difference
Claude Opus 4.5Winner51.2% ± 0.99
Claude Sonnet 4.549% ± 1.01
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for Claude Opus 4.5 and Claude Sonnet 4.5
No documented difference in the test setupVersion: 1Metric: TrueSkill ratingScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101 Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929
No documented difference in the test setupVersion: v4, commit f7cf735Metric: unweighted overall accuracyScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101-fc Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929-fcUnweighted overall score across agentic, multi-turn, and single-turn function-calling tests.
No documented difference in the test setupVersion: 45-paper public hard setMetric: automatic accuracyScoring: Higher is betterSettings: Agent: Claude Code, Harness: Claude CodeClaude Code on 45 public paper reproductions. Total cost is divided by 45.
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101 Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101 Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101 Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929
No documented difference in the test setupVersion: four multi-turn challenge typesMetric: rubric pass rateScoring: Higher is betterSettings: Reasoning: thinking, Attempts: pass@1Multi-turn conversations with binary task-specific rubrics.
No documented difference in the test setupVersion: French, Spanish, and Chinese releaseMetric: accuracyScoring: Higher is betterSettings: Reasoning: thinking, Attempts: pass@1Native, non-translated reasoning tasks with automatic evaluation.
Test setup not documented as identicalNo direct winnerVersion: full finance setMetric: weighted rubric scoreScoring: Higher is betterClaude Opus 4.5: Reasoning: thinking, Attempts: pass@1 Claude Sonnet 4.5: Attempts: pass@1600 finance tasks with task-specific rubrics and o4-mini as judge.
Test setup not documented as identicalNo direct winnerVersion: full legal setMetric: weighted rubric scoreScoring: Higher is betterClaude Opus 4.5: Reasoning: thinking, Attempts: pass@1 Claude Sonnet 4.5: Attempts: pass@1500 legal tasks with task-specific rubrics and o4-mini as judge.
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.5: Snapshot: claude-opus-4-5-20251101 Claude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929
No documented difference in the test setupVersion: 1,490-task releaseMetric: weighted rubric scoreScoring: Higher is betterSettings: Reasoning: thinking, Attempts: pass@11,490 tasks with weighted rubrics and Claude 4 Sonnet as judge.
No documented difference in the test setupVersion: 758 private prompt-image pairsMetric: rubric scoreScoring: Higher is betterSettings: Reasoning: thinking, Attempts: pass@1758 single-turn image-text tasks with structured yes-no rubrics.
Key to the marks:better valuebetter, but not conclusivetie
Our model tests
Our tests
Compare how the models respond to the same prompt. Each test shows the latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Claude Opus 4.5
A community classic for free-form SVG drawing.
Reasoning (requested): high
Current attempt
Run date
1 Oct 2026
API provider
openrouter
Requested API model
anthropic/claude-opus-4.5
API model reported in response
anthropic/claude-opus-4.5
Reasoning setting
high
Pinned endpoint
Anthropic | anthropic/claude-4.5-opus-20251124
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Response time
21.6 s
Visually reviewed. This individual test does not establish overall model quality.
Claude Sonnet 4.5
A community classic for free-form SVG drawing.
Reasoning (requested): high
Current attempt
Run date
1 Oct 2026
API provider
openrouter
Requested API model
anthropic/claude-sonnet-4.5
API model reported in response
anthropic/claude-sonnet-4.5
Reasoning setting
high
Pinned endpoint
Anthropic | anthropic/claude-4.5-sonnet-20250929
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Response time
30.2 s
Visually reviewed. This individual test does not establish overall model quality.
Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.
The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.
Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.
More matchups
Related LLM comparisons
Compare Claude Opus 4.5 and Claude Sonnet 4.5 with other leading models using the same data and benchmark logic.
