AIpedia
All models

#60 Claude Sonnet 4.5

Anthropic · Claude Sonnet 4.5

Released: · Source

Text; Coding; Reasoning

Use cases
Coding, Reasoning, Text
Accepts
No verified data
Produces
No verified data

Access

Anthropic · API Computing: Cloud

Price USD

ProviderPrice USDConditions
Anthropic · API$0.3 / 1M cache-read tokensStandard · Direct Claude API; base input, 5m/1h cache writes, cache hits and output have separate rates. Not a Claude/Claude Code subscription price.Source · 19.09.2026
Anthropic · API$3.75 / 1M cache-write tokensStandard · Direct Claude API; base input, 5m/1h cache writes, cache hits and output have separate rates. Not a Claude/Claude Code subscription price.Source · 19.09.2026
Anthropic · API$3 / 1M input tokensStandard · Direct Claude API; base input, 5m/1h cache writes, cache hits and output have separate rates. Not a Claude/Claude Code subscription price.Source · 19.09.2026
Anthropic · API$15 / 1M output tokensStandard · Direct Claude API; base input, 5m/1h cache writes, cache hits and output have separate rates. Not a Claude/Claude Code subscription price.Source · 19.09.2026

Evaluator & score

Epoch AI · ECI146.84

Composite index · published model-group index · 20.09.2026 · Higher is better

Snapshot: 2026-09-20 · 90% CI [145.46, 148.5]

Official Epoch AI index; combines own, third-party and developer-reported results. It is not a safety audit or a media-generation score.

Conditions

Epoch Capabilities Index; official model-group estimates

Official ECI model scores, Epoch AI, CC BY 4.0. Composite of own, third-party and developer-reported results. 90% bootstrap interval. Not a per-effort score; export date is the model release date, not measurement date. Methodology: https://epoch.ai/eci#documentation

Epoch AI · Chess Puzzles4 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Chess Puzzles; Epoch AI own run; best score across scorers

Epoch AI own run; Chess Puzzles; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: KB62zrQQ5ccd7hCcUwkX8j; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 06.08.2026

Epoch AI · Chess Puzzles12 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Chess Puzzles; Epoch AI own run; best score across scorers

Epoch AI own run; Chess Puzzles; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: 6qgxJVk8HHLppb7hPqz9Tv; file: chess_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 08.12.2025

Epoch AI · EBR-bench2.381 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

EBR-bench; Epoch AI own run; best score across scorers

Epoch AI own run; EBR-bench; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: cUQEu2ysx4CcVJHi9KtzjQ; file: ebr_bench.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 25.06.2026

Epoch AI · FrontierMath9.31 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-2025-02-28-Private; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: n26C8XHigC9Xfsdb24JZtd; file: frontiermath.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 16.11.2025

Epoch AI · FrontierMath15.225 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-2025-02-28-Private; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: LUpSd7DzWf3Fw4iwXb3MPV; file: frontiermath.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 16.11.2025

Epoch AI · FrontierMath13.495 %

Independent run · thinking budget 59K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-2025-02-28-Private; version: claude-sonnet-4-5-20250929_59K; mode: thinking budget 59K; source id: 3GzYKQW2K4iijm6a73rVeh; file: frontiermath.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 13.11.2025

Epoch AI · FrontierMath-Tier-4-2025-07-01-Private2.083 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tier-4-2025-07-01-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tier-4-2025-07-01-Private; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: 2o8XZ8V6W5jKD7TuY4frux; file: frontiermath_tier_4.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 29.09.2025

Epoch AI · FrontierMath-Tier-4-2025-07-01-Private4.167 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tier-4-2025-07-01-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tier-4-2025-07-01-Private; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: d8WWwzb6b57mWqddhBXuDi; file: frontiermath_tier_4.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 22.10.2025

Epoch AI · FrontierMath-Tier-4-v2-Private2.439 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tier-4-v2-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tier-4-v2-Private; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: d3m9Xip8cof4s77z6LKkEh; file: frontiermath_tier_4_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 11.06.2026

Epoch AI · FrontierMath-Tiers-1-3-v2-Private23.86 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

FrontierMath-Tiers-1-3-v2-Private; Epoch AI own run; best score across scorers

Epoch AI own run; FrontierMath-Tiers-1-3-v2-Private; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: 7oUkeLfwMK3MtkSNHX6QPu; file: frontiermath_tiers_1_3_v2.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 11.06.2026

Epoch AI · GPQA Diamond73.737 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

GPQA Diamond; Epoch AI own run; best score across scorers

Epoch AI own run; GPQA diamond; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: fsZmzw8jjyUgMQGwxodBwN; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 29.09.2025

Epoch AI · GPQA Diamond78.788 %

Independent run · thinking budget 16K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

GPQA Diamond; Epoch AI own run; best score across scorers

Epoch AI own run; GPQA diamond; version: claude-sonnet-4-5-20250929_16K; mode: thinking budget 16K; source id: LkVuUxvsHNzpcg3sUiH7f3; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 28.10.2025

Epoch AI · GPQA Diamond81.726 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

GPQA Diamond; Epoch AI own run; best score across scorers

Epoch AI own run; GPQA diamond; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: ii6JE9j57eSbuswEsJArTa; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 21.10.2025

Epoch AI · GPQA Diamond82.323 %

Independent run · thinking budget 59K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

GPQA Diamond; Epoch AI own run; best score across scorers

Epoch AI own run; GPQA diamond; version: claude-sonnet-4-5-20250929_59K; mode: thinking budget 59K; source id: XaGuWDxPtqVvyxqdMncKFj; file: gpqa_diamond.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 28.10.2025

Epoch AI · MATH level 597.734 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

MATH level 5; Epoch AI own run; best score across scorers

Epoch AI own run; MATH level 5; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: FqjAH25VNjgwQTbDJFfqAg; file: math_level_5.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 21.10.2025

Epoch AI · Mock AIME 2024/202535.556 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Mock AIME 2024/2025; Epoch AI own run; best score across scorers

Epoch AI own run; OTIS Mock AIME 2024-2025; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: dEVgttSw8u6Tt2RsPWTc3C; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 29.09.2025

Epoch AI · Mock AIME 2024/202571.111 %

Independent run · thinking budget 16K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Mock AIME 2024/2025; Epoch AI own run; best score across scorers

Epoch AI own run; OTIS Mock AIME 2024-2025; version: claude-sonnet-4-5-20250929_16K; mode: thinking budget 16K; source id: 7QkPRbRPpRx8nJT2ZcqSx6; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 28.10.2025

Epoch AI · Mock AIME 2024/202577.778 %

Independent run · thinking budget 32K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Mock AIME 2024/2025; Epoch AI own run; best score across scorers

Epoch AI own run; OTIS Mock AIME 2024-2025; version: claude-sonnet-4-5-20250929_32K; mode: thinking budget 32K; source id: kqTyhmHyT9irTAWk3xBt2x; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 21.10.2025

Epoch AI · Mock AIME 2024/202577.778 %

Independent run · thinking budget 59K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Mock AIME 2024/2025; Epoch AI own run; best score across scorers

Epoch AI own run; OTIS Mock AIME 2024-2025; version: claude-sonnet-4-5-20250929_59K; mode: thinking budget 59K; source id: k5PDL6MpCC6P5eLAhodJiS; file: otis_mock_aime_2024_2025.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 28.10.2025

Epoch AI · Mystery Game Puzzles17 %

Independent run · thinking budget 48K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

Mystery Game Puzzles; Epoch AI own run; best score across scorers

Epoch AI own run; Mystery Game Puzzles; version: claude-sonnet-4-5-20250929_48K; mode: thinking budget 48K; source id: 4oSbA2RKFsfuAfVayAMAww; file: mystery_game_puzzles.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 25.07.2026

Epoch AI · SWE-bench Verified71.281 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

SWE-bench Verified; Epoch AI own run; best score across scorers

Epoch AI own run; SWE-Bench verified; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: Lti64yMEsBWSzgEMFCSVhp; file: swe_bench_verified.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 05.02.2026

Epoch AI · SimpleQA Verified23.7 %

Independent run · default (effort unspecified by source) · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

SimpleQA Verified; Epoch AI own run; best score across scorers

Epoch AI own run; SimpleQA Verified; version: claude-sonnet-4-5-20250929; mode: default (effort unspecified by source); source id: MhqeuRVx4JcRfxPQDYPq7Z; file: simpleqa_verified.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 10.08.2026

Epoch AI · SimpleQA Verified30.7 %

Independent run · thinking budget 59K · 20.09.2026 · Higher is better

Snapshot: 2026-09-20

Conditions

SimpleQA Verified; Epoch AI own run; best score across scorers

Epoch AI own run; SimpleQA Verified; version: claude-sonnet-4-5-20250929_59K; mode: thinking budget 59K; source id: XQEGUQjpXupjdyKoGuSmum; file: simpleqa_verified.csv. CC BY 4.0, Epoch AI. Snapshot 2026-09-20. Source column Best score (across scorers), not AIpedia's selection of the best effort.

Measurement date: 27.08.2026

SourceVerified 18.09.2026