modelbench日本語

Claude Sonnet 4.6

AnthropicLegacy

Input price
$3.00
Per 1 million tokens (USD)
Output price
$15.00
Per 1 million tokens (USD)
Effort levels
4total
Default: High
Benchmark results
12total
Benchmark types: 5

Model information

API model ID
claude-sonnet-4-6
release date
Unknown
effort
Low / Med / High (default) / Max
Effort source
Based on Anthropic effort documentation (platform.claude.com/docs/en/build-with-claude/effort).
Claude Code
available
Codex
unavailable
Availability notes
`claude-sonnet-4-6[1m]` requires usage credits on all subscriptions. Codex's official model list (learn.chatgpt.com/docs/models) contains only OpenAI models, so codex is false (connections via a custom provider are not counted as official options).
Availability source
https://code.claude.com/docs/en/model-config

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input$3.00
output$15.00
cache read$0.30
cache write$3.75

cacheWritePerMTok is for a 5-minute cache write. 1h write $6.

Claude Sonnet 4.6 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok

Source: https://platform.claude.com/docs/en/about-claude/pricing

Benchmark results

BenchmarkeffortScoreSource cost (metric)measured/reported bysourceConditions and extraction method
GPQA DiamondMedMed83.3%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_medium, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-07-13T17:28:00.000ZLocation gpqa_diamond.csv, data row 165 (file line 235), id=e8MXnAM8HMF8eEzYtYA7xv, Model version=claude-sonnet-4-6_medium
GPQA DiamondHigh (default)High83.3%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_high, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-07-13T17:28:15.000ZLocation gpqa_diamond.csv, data row 162 (file line 232), id=DmdKPD9Z9RXwYyATAoG4Uw, Model version=claude-sonnet-4-6_high
GPQA DiamondMaxMax78.8%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_max, Best score (across scorers)=0.7878787878787878, stderr=0.029126522834586777, Started at=2026-08-06T22:21:09.000ZLocation gpqa_diamond.csv, data row 134 (file line 194), id=SEePRKRcv8oqn5HpD2KFxB, Model version=claude-sonnet-4-6_max
OTIS Mock AIME 2024-2025MedMed82.2%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=claude-sonnet-4-6_medium, Best score (across scorers)=0.8222222222222222, stderr=0.057637747950250916, Started at=2026-07-13T17:28:00.000ZLocation otis_mock_aime_2024_2025.csv, data row 173 (file line 248), id=kDNNbUYXhrAH5uDBGykFaf, Model version=claude-sonnet-4-6_medium
OTIS Mock AIME 2024-2025High (default)High75.6%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=claude-sonnet-4-6_high, Best score (across scorers)=0.7555555555555555, stderr=0.06478835438717, Started at=2026-07-13T17:28:15.000ZLocation otis_mock_aime_2024_2025.csv, data row 170 (file line 245), id=oXZ7ZVZtADrwFPKAe6zTvL, Model version=claude-sonnet-4-6_high
OTIS Mock AIME 2024-2025MaxMax71.1%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=claude-sonnet-4-6_max, Best score (across scorers)=0.7111111111111111, stderr=0.06832943242540508, Started at=2026-08-06T22:21:16.000ZLocation otis_mock_aime_2024_2025.csv, data row 143 (file line 208), id=XnQVH5qSfxVjpzoPwUEmnh, Model version=claude-sonnet-4-6_max
SimpleQA VerifiedHigh (default)High35.5%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptsimpleqa_verified.csv: Model version=claude-sonnet-4-6_high, Best score (across scorers)=0.355, stderr=0.015139491543780595, Started at=2026-08-10T22:42:23.000ZLocation simpleqa_verified.csv, data row 97 (file line 147), id=LJyKf8Xy4dymxNHbGLwNdA, Model version=claude-sonnet-4-6_high
SimpleQA VerifiedMaxMax32.8%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptsimpleqa_verified.csv: Model version=claude-sonnet-4-6_max, Best score (across scorers)=0.328, stderr=0.014853842487270312, Started at=2026-08-27T19:27:37.000ZLocation simpleqa_verified.csv, data row 89 (file line 139), id=Zs5fCvNzaz8LhqgwDSAztU, Model version=claude-sonnet-4-6_max
Chess Puzzles(Epoch AI)MedMed16.0%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptchess_puzzles.csv: Model version=claude-sonnet-4-6_medium, Best score (across scorers)=0.16, stderr=0.03684529491774706, Started at=2026-10-13T13:36:47.000ZLocation chess_puzzles.csv, data row 113 (file line 167), id=htvM9QKQJ8TfBxTzDxfZfp, Model version=claude-sonnet-4-6_medium
Chess Puzzles(Epoch AI)High (default)High19.0%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptchess_puzzles.csv: Model version=claude-sonnet-4-6_high, Best score (across scorers)=0.19, stderr=0.039427724440366255, Started at=2026-10-13T13:36:50.000ZLocation chess_puzzles.csv, data row 112 (file line 166), id=Atc4F5iuMZu3vNBWVGCBnv, Model version=claude-sonnet-4-6_high
Chess Puzzles(Epoch AI)MaxMax23.0%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptchess_puzzles.csv: Model version=claude-sonnet-4-6_max, Best score (across scorers)=0.23, stderr=0.04229525846816507, Started at=2026-10-13T13:44:15.000ZLocation chess_puzzles.csv, data row 95 (file line 146), id=6P9AJQmBzaPmE7ossbqLjz, Model version=claude-sonnet-4-6_max
Epoch Capabilities Index(ECI)not statednot stated152.86—Epoch AIEpoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from table
Source excerpteci_scores.csv: Model=Claude Sonnet 4.6, eci=152.86, eci_ci_low=151.17, eci_ci_high=154.65Location epoch_capabilities_index/eci_scores.csv, data row 56 (file line 57), Model=Claude Sonnet 4.6

Related rankings

References