Language modelActive

Claude Sonnet 4.5

Anthropic

Released: September 2025
Data date: September 8, 2026

Intelligence: Not ranked
Overall score
Speed: 43.8 tokens/s
Output throughput
Price: $3 · $15
Input · Output / 1M tokens
Input: Text, Image
Output: Text

No published category-wide ranking is available for this model.

Entries 1-12 of 42. Page 1 of 4.

Published benchmarks

Each chart compares models in the same documented test and highlights the current model.

BFCL v4

Overall

What this benchmark measures: Berkeley's function-calling test combines single and multi-turn tool calls with web search, memory, and hallucination measurement.

Context: The overall score is an unweighted mix of subcategories and depends on native function calling or prompt workarounds.

Higher is better2 modelsClaude Sonnet 4.5: Rank 2 of 2Data date: September 2, 2026

1.Claude Opus 4.577.47%

2.Claude Sonnet 4.573.24%

Scale: 0% - 100%

Source: Berkeley BFCL

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: bfcl-v4-f7cf735-overall
Metric: unweighted overall accuracy
Scale: 0-100
Participants: 2
Methodology and context: Unweighted overall score across agentic, multi-turn, and single-turn function-calling tests.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Model snapshot: claude-sonnet-4-5-20250929-fc. Evaluator: Berkeley BFCL. Dataset type: public. Leaderboard date: 2026-04-12. Source ID: berkeley-bfcl. Evidence capture ID: curated-berkeley-bfcl-2026-09-02-171020422eb3. Source payload hash: 171020422eb31aa497dbf9dd95b72c153c0db68a3eceec63a4c059bade96f4c2. Parser version: curated-v1. Imported at: 2026-09-04

Source: Berkeley BFCL

Coding

2 measurements

CORE-Bench Hard

Automatic validation

What this benchmark measures: 45 public tasks for reproducing research results with code, data, and dependencies.

Context: Automatic and manually validated scores are different metrics. The agent scaffold strongly affects the score.

Higher is better2 modelsClaude Sonnet 4.5: Rank 2 of 2Data date: August 6, 2026

1.Claude Opus 4.577.78%

2.Claude Sonnet 4.562.22%

Scale: 0% - 100%

Source: Princeton HAL

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: hal-corebench-hard-claude-code-automatic
Metric: automatic accuracy
Scale: 0-100
Participants: 2
Methodology and context: Claude Code on 45 public paper reproductions. Total cost is divided by 45.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Princeton HAL. Dataset type: public. Harness: Claude Code. Agent: Claude Code. Cost per task in USD: 1.5184444444444445. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-d289e35e619a. Source payload hash: d289e35e619aac7b28355c86830d55c245fc6b287e2327069860ac0522c95e8b. Parser version: curated-v1. Imported at: 2026-09-04

Source: Princeton HAL

SciCode

Accuracy

What this benchmark measures: 65 scientific coding problems with 338 subproblems across 16 research fields.

Context: Zero Shot, Tool Calling, and HAL Generalist are not directly comparable scaffolds.

Higher is better4 modelsClaude Sonnet 4.5: Rank 3 of 4Data date: August 5, 2026

1.o39.23%

2.GPT-56.15%

3.Claude Sonnet 4.53.08%

4.GPT-4.11.54%

Scale: 0% - 100%

Source: Princeton HAL

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: hal-scicode-scicode-tool-calling-overall
Metric: accuracy
Scale: 0-100
Participants: 4
Methodology and context: SciCode Tool Calling on 65 main scientific problems. Total cost is divided by 65.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Princeton HAL. Dataset type: public. Harness: SciCode Tool Calling. Agent: SciCode Tool Calling. Cost per task in USD: 1.6044615384615386. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-05-c67a4c4ed842. Source payload hash: c67a4c4ed8428dfb71febdf30c9d21b46b0644189ef4d4de5ce334f3f2edc12c. Parser version: curated-v1. Imported at: 2026-09-04

Source: Princeton HAL

Cybersecurity

2 measurements

MT-AgentRisk

Attack success rate

What this benchmark measures: 365 harmful sequences test safety risks in multi-turn tool use.

Context: A lower attack success rate is better. Capability and safety are separate dimensions.

Note (Claude Sonnet 4.5): Table 4 reports a 15.43% refusal rate, while Table 9 in the same paper reports 15.34%. This row uses the direct single-turn versus multi-turn comparison table.

Lower is better3 modelsClaude Sonnet 4.5: Rank 1 of 3Data date: August 9, 2026

1.Claude Sonnet 4.571.78%

2.Gemini 3 Flash78.9%

3.DeepSeek-V3.284.93%

Scale: 0% - 100%

Source: MT-AgentRisk

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: mt-agent-risk:multi-turn:asr
Metric: attack success rate
Scale: 0-100
Participants: 3
Methodology and context: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MT-AgentRisk. Dataset type: public. Leaderboard date: 2026-02-13. Harness: OpenHands. Source ID: mt-agent-risk. Evidence capture ID: curated-mt-agent-risk-2026-08-09-f550ff9bf634. Source payload hash: f550ff9bf6346dc509fb04e302b64acda7943dd7e5863a5ca3206286480a11a5. Parser version: curated-v1. Imported at: 2026-09-04

Source: MT-AgentRisk

MT-AgentRisk

Refusal rate

What this benchmark measures: 365 harmful sequences test safety risks in multi-turn tool use.

Context: A lower attack success rate is better. Capability and safety are separate dimensions.

Note (Claude Sonnet 4.5): Table 4 reports a 15.43% refusal rate, while Table 9 in the same paper reports 15.34%. This row uses the direct single-turn versus multi-turn comparison table.

Higher is better3 modelsClaude Sonnet 4.5: Rank 1 of 3Data date: August 9, 2026

1.Claude Sonnet 4.515.43%

2.Gemini 3 Flash6.03%

3.DeepSeek-V3.21.1%

Scale: 0% - 100%

Source: MT-AgentRisk

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: mt-agent-risk:multi-turn:refusal
Metric: refusal rate
Scale: 0-100
Participants: 3
Methodology and context: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MT-AgentRisk. Dataset type: public. Leaderboard date: 2026-02-13. Harness: OpenHands. Source ID: mt-agent-risk. Evidence capture ID: curated-mt-agent-risk-2026-08-09-9e7ba7aa3157. Source payload hash: 9e7ba7aa3157bc30470265facc4bb25edf1a9b2f6cf7b733102470330ed4b034. Parser version: curated-v1. Imported at: 2026-09-04

Source: MT-AgentRisk

MultiChallenge

Overall

What this benchmark measures: Multi-turn conversations test memory, instruction retention, versioned editing, and self-coherence.

Context: Tasks were selected from shared failures of six older frontier models and may disadvantage those systems.

Higher is better8 modelsClaude Sonnet 4.5: Rank 8 of 8Data date: August 26, 2026

1.Gemini 3.1 Pro Preview71.37%

2.GPT-5.4 Pro69.23%

3.GPT-563.19%

4.o3-pro62.4%

5.Claude Opus 4.558.97%

6.o356.62%

7.Claude Opus 4.656.02%

8.Claude Sonnet 4.555.32%

Scale: 0% - 100%

Source: Scale AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: scale-multichallenge-overall
Metric: rubric pass rate
Scale: 0-100
Participants: 8
Methodology and context: Multi-turn conversations with binary task-specific rubrics.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: thinking. Score display: 55.32% ± 1.47. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-93c4c6df84ba. Source payload hash: 93c4c6df84baa57ecc302765b454f1d1d402750d6ee8968f2085772a44e192b1. Parser version: curated-v1. Imported at: 2026-09-04

Source: Scale AI

PRBench Finance

Overall

What this benchmark measures: 600 realistic finance questions with weighted criteria, including a 300-question hard subset.

Context: An o4-mini judge scores the responses, so domain correctness and operational reliability remain separate questions.

Higher is better16 modelsClaude Sonnet 4.5: Rank 10 of 16Data date: August 26, 2026

1.Claude Fable 553.86%

2.Claude Opus 4.653.28%

3.GPT-551.32%

4.GPT-5 pro51.06%

5.GPT-5.6 Sol50.45%

6.o3-pro49.08%

7.o347.69%

8.Claude Opus 4.546.16%

9.GPT-5.445.63%

10.Claude Sonnet 4.543.79%

11.Gemini 3.1 Pro Preview41.87%

12.o4-mini39.22%

13.Gemini 2.5 Pro38.92%

14.Gemini 2.5 Flash38.41%

15.GPT-4.134.32%

16.Llama 4 Maverick22.36%

Scale: 0% - 100%

Source: Scale AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: scale-prbench-finance-full
Metric: weighted rubric score
Scale: 0-100
Participants: 16
Methodology and context: 600 finance tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 43.79% ± 0.4. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-db93e34ac02d. Source payload hash: db93e34ac02d5628c3ec931b3f6d17257e1b7695c21cf8aee846e136474ca9b9. Parser version: curated-v1. Imported at: 2026-09-04

Source: Scale AI

PRBench Legal

Overall

What this benchmark measures: 500 realistic legal questions with weighted criteria across jurisdictions and practice areas.

Context: The benchmark measures professional response quality but cannot replace legal review or human accountability.

Higher is better16 modelsClaude Sonnet 4.5: Rank 13 of 16Data date: August 26, 2026

1.Claude Fable 552.56%

2.Claude Opus 4.652.27%

3.GPT-5.6 Sol50.5%

4.GPT-5 pro49.89%

5.o3-pro49.67%

6.GPT-548.96%

7.o348.57%

8.GPT-5.444.35%

9.Claude Opus 4.544.21%

10.Gemini 3.1 Pro Preview44.02%

11.Gemini 2.5 Pro41.43%

12.Gemini 2.5 Flash41.02%

13.Claude Sonnet 4.540.84%

14.o4-mini38.11%

15.GPT-4.136.48%

16.Llama 4 Maverick24.84%

Scale: 0% - 100%

Source: Scale AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: scale-prbench-legal-full
Metric: weighted rubric score
Scale: 0-100
Participants: 16
Methodology and context: 500 legal tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 40.84% ± 0.4. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-cfd9f8c7d859. Source payload hash: cfd9f8c7d85930ec8d7acf7515a8200c29b116b3913b0affc48e4e68b3103115. Parser version: curated-v1. Imported at: 2026-09-04

Source: Scale AI

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

CORE-Bench Hard: Automatic validation (Show measurement, test conditions, and source)

Source value: 44.44
Score: 44.44
Metric: automatic accuracy
Unit: %
Benchmark version: 45-paper public hard set
Category: coding
Task: automatic
Task label: Automatic validation
Direction: Higher is better
Comparison cohort: hal-corebench-hard-core-agent-automatic
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: CORE-Agent on 45 public paper reproductions. Total cost is divided by 45.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Princeton HAL. Dataset type: public. Harness: CORE-Agent. Agent: CORE-Agent. Cost per task in USD: 2.052. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-338fc6c016cb. Source payload hash: 338fc6c016cbec4209b3ca33757424adc5b86974ca4ce825ab4c08f7af37f8c5. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: CORE-Agent on 45 public paper reproductions. Total cost is divided by 45.

Source Princeton HAL

MCP-Universe: Evaluator score (Show measurement, test conditions, and source)

Source value: 54.38
Score: 54.38
Metric: average evaluator score
Unit: %
Benchmark version: official site capture 2026-08-09
Category: agentic
Task: evaluator
Task label: Evaluator score
Direction: Higher is better
Comparison cohort: mcp-universe:native-function-call:evaluator
Source type: official-leaderboard
Evaluator: MCP-Universe
Status: active
Retrieved at: 2026-08-09
Methodology: Execution-based evaluators. ReAct and native function-call cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MCP-Universe. Dataset type: public. Source ID: mcp-universe. Evidence capture ID: curated-mcp-universe-2026-08-09-f3d0dc2c2491. Source payload hash: f3d0dc2c24919b5cca24bbefffc86f3433b0737e9314be6a595a7d24880d3aff. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: Execution-based evaluators. ReAct and native function-call cohorts remain separate.

Source MCP-Universe

MCP-Universe: Task success (Show measurement, test conditions, and source)

Source value: 35.06
Score: 35.06
Metric: task success rate
Unit: %
Benchmark version: official site capture 2026-08-09
Category: agentic
Task: success
Task label: Task success
Direction: Higher is better
Comparison cohort: mcp-universe:native-function-call:success
Source type: official-leaderboard
Evaluator: MCP-Universe
Status: active
Retrieved at: 2026-08-09
Methodology: Execution-based evaluators. ReAct and native function-call cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MCP-Universe. Dataset type: public. Source ID: mcp-universe. Evidence capture ID: curated-mcp-universe-2026-08-09-364c94147e9a. Source payload hash: 364c94147e9ac55d8449117dbbee9ad4648cfffca2173a06a6ae236e6bf6d2ca. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: Execution-based evaluators. ReAct and native function-call cohorts remain separate.

Source MCP-Universe

MT-AgentRisk: Attack success rate (Show measurement, test conditions, and source)

Source value: 44.66
Score: 44.66
Metric: attack success rate
Unit: %
Benchmark version: ICML 2026 paper
Category: cybersecurity
Task: asr
Task label: Attack success rate
Direction: Lower is better
Comparison cohort: mt-agent-risk:single-turn:asr
Source type: independent-evaluator
Evaluator: MT-AgentRisk
Status: active
Retrieved at: 2026-08-09
Methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MT-AgentRisk. Dataset type: public. Leaderboard date: 2026-02-13. Harness: OpenHands. Source ID: mt-agent-risk. Evidence capture ID: curated-mt-agent-risk-2026-08-09-47f14ee18e72. Source payload hash: 47f14ee18e7288e62796e1835eadb1033199f50054a3144b2cc0f674c8547480. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.

Source MT-AgentRisk

Recorded measurement details

Every observation retains its source value and published test conditions.

BFCL v4: Overall (Show measurement, test conditions, and source)

Source value: 73.24
Score: 73.24
Metric: unweighted overall accuracy
Unit: %
Benchmark version: v4, commit f7cf735
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: bfcl-v4-f7cf735-overall
Source type: official-leaderboard
Evaluator: Berkeley BFCL
Status: active
Retrieved at: 2026-09-02
Methodology: Unweighted overall score across agentic, multi-turn, and single-turn function-calling tests.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Model snapshot: claude-sonnet-4-5-20250929-fc. Evaluator: Berkeley BFCL. Dataset type: public. Leaderboard date: 2026-04-12. Source ID: berkeley-bfcl. Evidence capture ID: curated-berkeley-bfcl-2026-09-02-171020422eb3. Source payload hash: 171020422eb31aa497dbf9dd95b72c153c0db68a3eceec63a4c059bade96f4c2. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: Unweighted overall score across agentic, multi-turn, and single-turn function-calling tests.

Source Berkeley BFCL

CORE-Bench Hard: Automatic validation (Show measurement, test conditions, and source)

Source value: 62.22
Score: 62.22
Metric: automatic accuracy
Unit: %
Benchmark version: 45-paper public hard set
Category: coding
Task: automatic
Task label: Automatic validation
Direction: Higher is better
Comparison cohort: hal-corebench-hard-claude-code-automatic
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-06
Methodology: Claude Code on 45 public paper reproductions. Total cost is divided by 45.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Princeton HAL. Dataset type: public. Harness: Claude Code. Agent: Claude Code. Cost per task in USD: 1.5184444444444445. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-06-d289e35e619a. Source payload hash: d289e35e619aac7b28355c86830d55c245fc6b287e2327069860ac0522c95e8b. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: Claude Code on 45 public paper reproductions. Total cost is divided by 45.

Source Princeton HAL

SciCode: Accuracy (Show measurement, test conditions, and source)

Source value: 3.08
Score: 3.08
Metric: accuracy
Unit: %
Benchmark version: 65-problem main set
Category: coding
Task: overall
Task label: Accuracy
Direction: Higher is better
Comparison cohort: hal-scicode-scicode-tool-calling-overall
Source type: independent-evaluator
Evaluator: Princeton HAL
Status: active
Retrieved at: 2026-08-05
Methodology: SciCode Tool Calling on 65 main scientific problems. Total cost is divided by 65.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Princeton HAL. Dataset type: public. Harness: SciCode Tool Calling. Agent: SciCode Tool Calling. Cost per task in USD: 1.6044615384615386. Source ID: princeton-hal. Evidence capture ID: curated-princeton-hal-2026-08-05-c67a4c4ed842. Source payload hash: c67a4c4ed8428dfb71febdf30c9d21b46b0644189ef4d4de5ce334f3f2edc12c. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: SciCode Tool Calling on 65 main scientific problems. Total cost is divided by 65.

Source Princeton HAL

MT-AgentRisk: Attack success rate (Show measurement, test conditions, and source)

Source value: 71.78
Score: 71.78
Metric: attack success rate
Unit: %
Benchmark version: ICML 2026 paper
Category: cybersecurity
Task: asr
Task label: Attack success rate
Direction: Lower is better
Comparison cohort: mt-agent-risk:multi-turn:asr
Source type: independent-evaluator
Evaluator: MT-AgentRisk
Status: active
Retrieved at: 2026-08-09
Methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MT-AgentRisk. Dataset type: public. Leaderboard date: 2026-02-13. Harness: OpenHands. Source ID: mt-agent-risk. Evidence capture ID: curated-mt-agent-risk-2026-08-09-f550ff9bf634. Source payload hash: f550ff9bf6346dc509fb04e302b64acda7943dd7e5863a5ca3206286480a11a5. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.
Context: Table 4 reports a 15.43% refusal rate, while Table 9 in the same paper reports 15.34%. This row uses the direct single-turn versus multi-turn comparison table.

Source MT-AgentRisk

MT-AgentRisk: Refusal rate (Show measurement, test conditions, and source)

Source value: 15.43
Score: 15.43
Metric: refusal rate
Unit: %
Benchmark version: ICML 2026 paper
Category: cybersecurity
Task: refusal
Task label: Refusal rate
Direction: Higher is better
Comparison cohort: mt-agent-risk:multi-turn:refusal
Source type: independent-evaluator
Evaluator: MT-AgentRisk
Status: active
Retrieved at: 2026-08-09
Methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: MT-AgentRisk. Dataset type: public. Leaderboard date: 2026-02-13. Harness: OpenHands. Source ID: mt-agent-risk. Evidence capture ID: curated-mt-agent-risk-2026-08-09-9e7ba7aa3157. Source payload hash: 9e7ba7aa3157bc30470265facc4bb25edf1a9b2f6cf7b733102470330ed4b034. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: OpenHands without a defense layer, judged by GPT-4.1. Single-turn and multi-turn cohorts remain separate.
Context: Table 4 reports a 15.43% refusal rate, while Table 9 in the same paper reports 15.34%. This row uses the direct single-turn versus multi-turn comparison table.

Source MT-AgentRisk

MultiChallenge: Overall (Show measurement, test conditions, and source)

Source value: 55.32
Score: 55.32
Metric: rubric pass rate
Unit: %
Benchmark version: four multi-turn challenge types
Category: productivity
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: scale-multichallenge-overall
Confidence interval: 1.47
Source type: official-leaderboard
Evaluator: Scale AI
Status: active
Retrieved at: 2026-08-26
Methodology: Multi-turn conversations with binary task-specific rubrics.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Reasoning effort: thinking. Score display: 55.32% ± 1.47. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-93c4c6df84ba. Source payload hash: 93c4c6df84baa57ecc302765b454f1d1d402750d6ee8968f2085772a44e192b1. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: Multi-turn conversations with binary task-specific rubrics.

Source Scale AI

PRBench Finance: Overall (Show measurement, test conditions, and source)

Source value: 43.79
Score: 43.79
Metric: weighted rubric score
Unit: %
Benchmark version: full finance set
Category: finance
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: scale-prbench-finance-full
Confidence interval: 0.4
Source type: official-leaderboard
Evaluator: Scale AI
Status: active
Retrieved at: 2026-08-26
Methodology: 600 finance tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 43.79% ± 0.4. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-db93e34ac02d. Source payload hash: db93e34ac02d5628c3ec931b3f6d17257e1b7695c21cf8aee846e136474ca9b9. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: 600 finance tasks with task-specific rubrics and o4-mini as judge.

Source Scale AI

PRBench Legal: Overall (Show measurement, test conditions, and source)

Source value: 40.84
Score: 40.84
Metric: weighted rubric score
Unit: %
Benchmark version: full legal set
Category: legal
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: scale-prbench-legal-full
Confidence interval: 0.4
Source type: official-leaderboard
Evaluator: Scale AI
Status: active
Retrieved at: 2026-08-26
Methodology: 500 legal tasks with task-specific rubrics and o4-mini as judge.. Source model ID: curated/claude-sonnet-4.5. Source model name: Claude Sonnet 4.5. Provider reported by source: Anthropic. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 40.84% ± 0.4. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-cfd9f8c7d859. Source payload hash: cfd9f8c7d85930ec8d7acf7515a8200c29b116b3913b0affc48e4e68b3103115. Parser version: curated-v1. Imported at: 2026-09-04
Comparison methodology: 500 legal tasks with task-specific rubrics and o4-mini as judge.

Source Scale AI

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Sonnet 4.5

Not tested yet

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

Evidence

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Speed: Anthropic, Non-reasoning. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026.
Artificial Analysis Methodology
Price: Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
Pricing
Input: Documented modalities. Retrieved September 8, 2026.
Model documentation
Output: Documented modalities. Retrieved September 8, 2026.
Model documentation

Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.

Open evidence questions and research notes (original wording)

Not found in the inspected sources

parameters-billions. Anthropic does not publish parameter counts for this model.

Not found in the inspected sources

active-parameters-billions. Anthropic does not publish active parameter counts for this model.

Model metadataSource
Context window dataSource
API pricingSource
Berkeley BFCL (retrieved September 2, 2026)Source
Princeton HAL (retrieved August 5, 2026)Source
Princeton HAL (retrieved August 6, 2026)Source
Princeton HAL (retrieved August 5, 2026)Source
Princeton HAL (retrieved August 6, 2026)Source
Princeton HAL (retrieved August 5, 2026)Source
MCP-Universe (retrieved August 9, 2026)Source
MT-AgentRisk (retrieved August 9, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Scale AI (retrieved August 26, 2026)Source
Anthropic (retrieved September 8, 2026)Source
Artificial Analysis (retrieved September 8, 2026)Source
Model metadata (retrieved September 8, 2026)Source
Speed measurement methodologySource

Claude Sonnet 4.5

Published benchmarks

BFCL v4

Coding

CORE-Bench Hard

SciCode

Cybersecurity

MT-AgentRisk

MT-AgentRisk

MultiChallenge

PRBench Finance

PRBench Legal

Measurements without matching peer values

Recorded measurement details

Community tests you can inspect

Pelican on a bicycle

Specifications and access

Additional source observations

Published prices

100 API requests

Compare this model

Sources and data date