DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV

[ MODEL — anthropic / DC Model Index ]

Claude Sonnet 4.5 (latest)

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Update delayed · last successful import · 437 models · Sources & methodology ↗

anthropic · Released 2025-09-29

Claude Sonnet 4.5 (latest)
—

DC Power

0% fixed panel · Power withheld
—

DC Eco

—

DC Overall

Coding

—

0% · partial

Reasoning

—

0% · partial

Agents

—

0% · partial

1M context · $3 / $15

USD per 1M input / output tokens

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Evidence & available offers →

Available offers & pricing

Catalogue listings are not a guarantee of deployability. Azure quota tier, regional capacity and account eligibility require a separate account-specific check. No account information is included here.

ProviderInput / output per 1MRegion / deploymentQuota tier
OpenRouter ↗anthropic/claude-sonnet-4.5$3 / $15Not verified / On-demandAccount-specific
anthropic ↗claude-sonnet-4-5$3 / $15Not verified / Not verifiedAccount-specific

Reference task estimate: $0.024 for 3,000 input + 1,000 output tokens. Cache reads: $0.3 / 1M tokens where listed.

Supplementary ECI index · 0% of Power

Epoch Capabilities Index: 147.56 · published 90% interval 146.17–149.03

0 ECI benchmarks; mixed source configurations. Overlapping intervals do not establish superiority or equivalence.

Epoch AI methodology & data ↗

DC Power is withheld because the fixed independent-source panel is incomplete. Inspect the missing inputs below.

Use Claude Sonnet 4.5 (latest) as the comparison reference →
Inspect Claude Sonnet 4.5 (latest): weights, inputs & missing evidence

Fixed-panel coverage: 0%. Power, Eco and Overall are withheld until every panel is available. Partial domain values use only available panels and are not directly comparable with complete domain scores. ECI contributes 0%.

Coding: — · 35% of Power · 0% coverage · PARTIAL

LiveBench 2 Coding · 25 Oct 2026 · 50% of Coding = 17.5% of Power · —

Missing: LiveBench 2 Coding · 20261025: no eligible original observation

Epoch AI original MirrorCode · 50% of Coding = 17.5% of Power · —

Missing: MirrorCode: no eligible original observation

Reasoning: — · 35% of Power · 0% coverage · PARTIAL

LiveBench 2 Reasoning · 25 Oct 2026 · 40% of Reasoning = 14.0% of Power · —

Missing: LiveBench 2 Reasoning · 20261025: no eligible original observation

Epoch AI original reasoning panel · 30% of Reasoning = 10.5% of Power · —

Missing: Chess Puzzles: no eligible original observation

Missing: FrontierMath-Tiers-1-3-v2-Private: no eligible original observation

Missing: OTIS Mock AIME 2024-2025: no eligible original observation

ARC Prize · ARC-AGI-2 semi-private · 30% of Reasoning = 10.5% of Power · —

Missing: ARC-AGI-2 · semi-private: no eligible original observation

Agents: — · 30% of Power · 0% coverage · PARTIAL

LiveBench 2 Long Agentic · 25 Oct 2026 · 50% of Agents = 15.0% of Power · —

Missing: LiveBench 2 Long Agentic · 20261025: no eligible original observation

Terminal-Bench 4.0 · published model + agent · 50% of Agents = 15.0% of Power · —

Missing: Terminal-Bench 4.0: no eligible original observation

Power — · incomplete fixed panel. Missing scores are not zero.

Original benchmark observations

31 benchmarks · 71 observations. Each configuration stays separate. These are original percentages, before ECI chance and ceiling adjustments. Expand a score to inspect its source and conditions.

BenchmarkScoreEffort / harnessSource
GPQA diamondKnowledge
78.79%

claude-sonnet-4-5-20250929_16K

Epoch AI evaluation · epoch-run

Run: 2025-10-28 · gpqa_diamond.csv

Reported standard error: ±2.91 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
82.32%

claude-sonnet-4-5-20250929_59K

Epoch AI evaluation · epoch-run

Run: 2025-10-28 · gpqa_diamond.csv

Reported standard error: ±2.72 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
81.73%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2025-10-21 · gpqa_diamond.csv

Reported standard error: ±2.76 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
73.74%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2025-09-29 · gpqa_diamond.csv

Reported standard error: ±3.14 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-2025-02-28-PrivateReasoning
9.31%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2025-11-16 · frontiermath.csv

Reported standard error: ±1.71 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-2025-02-28-PrivateReasoning
15.22%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2025-11-16 · frontiermath.csv

Reported standard error: ±2.12 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-2025-02-28-PrivateReasoning
13.49%

claude-sonnet-4-5-20250929_59K

Epoch AI evaluation · epoch-run

Run: 2025-11-13 · frontiermath.csv

Reported standard error: ±2.01 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-Tier-4-2025-07-01-PrivateReasoning
4.17%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2025-10-22 · frontiermath_tier_4.csv

Reported standard error: ±2.91 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-Tier-4-2025-07-01-PrivateReasoning
2.08%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2025-09-29 · frontiermath_tier_4.csv

Reported standard error: ±2.08 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-Tiers-1-3-v2-PrivateReasoning
23.86%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2026-06-11 · frontiermath_tiers_1_3_v2.csv

Reported standard error: ±2.53 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-Tier-4-v2-PrivateReasoning
2.44%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2026-06-11 · frontiermath_tier_4_v2.csv

Reported standard error: ±2.44 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
MATH level 5Reasoning
97.73%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2025-10-21 · math_level_5.csv

Reported standard error: ±0.41 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
77.78%

claude-sonnet-4-5-20250929_59K

Epoch AI evaluation · epoch-run

Run: 2025-10-28 · otis_mock_aime_2024_2025.csv

Reported standard error: ±6.27 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
71.11%

claude-sonnet-4-5-20250929_16K

Epoch AI evaluation · epoch-run

Run: 2025-10-28 · otis_mock_aime_2024_2025.csv

Reported standard error: ±6.83 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
77.78%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2025-10-21 · otis_mock_aime_2024_2025.csv

Reported standard error: ±6.27 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
35.56%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2025-09-29 · otis_mock_aime_2024_2025.csv

Reported standard error: ±7.22 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
SWE-Bench verifiedCoding
71.28%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2026-02-05 · swe_bench_verified.csv

Reported standard error: ±2.06 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
SimpleQA VerifiedKnowledge
30.70%

claude-sonnet-4-5-20250929_59K

Epoch AI evaluation · epoch-run

Run: 2026-08-27 · simpleqa_verified.csv

Reported standard error: ±1.46 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
SimpleQA VerifiedKnowledge
23.70%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2026-08-10 · simpleqa_verified.csv

Reported standard error: ±1.35 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
10.00%

claude-sonnet-4-5-20250929_59K

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±3.02 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
10.00%

claude-sonnet-4-5-20250929_32K

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±3.02 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
6.00%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±2.39 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
EBR-benchOther
2.38%

claude-sonnet-4-5-20250929

Epoch AI evaluation · epoch-run

Run: 2026-06-25 · ebr_bench.csv

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
Mystery Game PuzzlesReasoning
17.00%

claude-sonnet-4-5-20250929_48K

Epoch AI evaluation · epoch-run

Run: 2026-07-25 · mystery_game_puzzles.csv

Reported standard error: ±3.78 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
ARC-AGIReasoning
63.67%

claude-sonnet-4-5-20250929_32K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGIReasoning
48.33%

claude-sonnet-4-5-20250929_16K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGIReasoning
46.50%

claude-sonnet-4-5-20250929_8K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGIReasoning
31.00%

claude-sonnet-4-5-20250929_1K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGIReasoning
25.50%

claude-sonnet-4-5-20250929

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
CybenchCoding
60.00%

claude-sonnet-4-5-20250929_unknown

Opus 4.5 System Card · external

Run: Date not supplied · cybench_external.csv

Results from Opus 4.5 system card, also reported on the official Cybench leaderboard

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
CybenchCoding
55.00%

claude-sonnet-4-5-20250929

Cybench leaderboard · external

Run: Date not supplied · cybench_external.csv

Thinking level unknown. "Results for Claude 4.5 Sonnet, Claude 4.1 Opus, Claude 4 Opus, and Claude 4 Sonnet are from the Claude 4.5 Sonnet System Card on a subset of 37 problems. Percentages are estimates based on probability of success on 1 trial."

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
DeepResearch BenchAgents
52.60%

claude-sonnet-4-5-20250929_2K

DeepResearchBench Leaderboard · external

Run: Date not supplied · deepresearchbench_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
DeepResearch BenchAgents
47.50%

claude-sonnet-4-5-20250929_low

https://evals.futuresearch.ai/#drb · external

Run: Date not supplied · deepresearchbench_external.csv

Inspect source ↗

CC BY 4.0

low / Not reportedExternal · via Epoch ↗
GSO-BenchCoding
14.71%

claude-sonnet-4-5-20250929_unknown

https://gso-bench.github.io/index.html · external

Run: Date not supplied · gso_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
GSO-BenchCoding
14.70%

claude-sonnet-4-5-20250929

GSO Leaderboard · external

Run: Date not supplied · gso_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
OSWorldAgents
62.90%

claude-sonnet-4-5-20250929

OS World Website · external

Run: Date not supplied · os_world_external.csv

Inspect source ↗

CC BY 4.0

unspecified / claude-sonnet-4-5-20250929 (100 steps)External · via Epoch ↗
OSWorldAgents
58.10%

claude-sonnet-4-5-20250929

OS World Website · external

Run: Date not supplied · os_world_external.csv

Inspect source ↗

CC BY 4.0

unspecified / claude-sonnet-4-5-20250929 (50 steps)External · via Epoch ↗
OSWorldAgents
42.90%

claude-sonnet-4-5-20250929

OS World Website · external

Run: Date not supplied · os_world_external.csv

Inspect source ↗

CC BY 4.0

unspecified / claude-sonnet-4-5-20250929 (15 steps)External · via Epoch ↗
SimpleBenchReasoning
54.30%

claude-sonnet-4-5-20250929_12K

SimpleBench Leaderboard · external

Run: Date not supplied · simplebench_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
SimpleBenchReasoning
54.30%

claude-sonnet-4-5-20250929_unknown

SimpleBench Leaderboard · external

Run: Date not supplied · simplebench_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
Terminal BenchCoding
46.52%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.35 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / CAMEL-AIExternal · via Epoch ↗
Terminal BenchCoding
43.15%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.59 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / GooseExternal · via Epoch ↗
Terminal BenchCoding
42.81%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.79 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Terminus 2External · via Epoch ↗
Terminal BenchCoding
42.80%

claude-sonnet-4-5-20250929

Terminal-Bench v2 Leaderboard · external

Run: 2025-10-31 · terminalbench_external.csv

Reported standard error: ±2.80 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Terminus 2 External · via Epoch ↗
Terminal BenchCoding
42.70%

claude-sonnet-4-5-20250929_unknown

External result; evaluator not specified · external

Run: 2026-01-04 · terminalbench_external.csv

Inspect source ↗

CC BY 4.0

unknown / MAYAExternal · via Epoch ↗
Terminal BenchCoding
42.70%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Inspect source ↗

CC BY 4.0

unknown / MAYA-V2External · via Epoch ↗
Terminal BenchCoding
42.60%

claude-sonnet-4-5-20250929

Terminal-Bench v2 Leaderboard · external

Run: 2025-11-02 · terminalbench_external.csv

Reported standard error: ±2.80 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / OpenHands External · via Epoch ↗
Terminal BenchCoding
42.58%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.77 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / OpenHandsExternal · via Epoch ↗
Terminal BenchCoding
42.53%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.81 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Mini-SWE-AgentExternal · via Epoch ↗
Terminal BenchCoding
42.50%

claude-sonnet-4-5-20250929

Terminal-Bench v2 Leaderboard · external

Run: 2025-11-03 · terminalbench_external.csv

Reported standard error: ±2.80 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Mini-SWE-Agent External · via Epoch ↗
Terminal BenchCoding
40.10%

claude-sonnet-4-5-20250929

Terminal-Bench v2 Leaderboard · external

Run: 2025-11-04 · terminalbench_external.csv

Reported standard error: ±2.90 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Claude Code External · via Epoch ↗
Terminal BenchCoding
40.06%

claude-sonnet-4-5-20250929_unknown

https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external

Run: 2025-09-29 · terminalbench_external.csv

Reported standard error: ±2.92 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Claude CodeExternal · via Epoch ↗
VPCTOther
39.80%

claude-sonnet-4-5-20250929_32K

VPCT leaderboard · external

Run: Date not supplied · vpct_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
VPCTOther
38.00%

claude-sonnet-4-5-20250929

VPCT leaderboard · external

Run: Date not supplied · vpct_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
WeirdMLCoding
47.71%

claude-sonnet-4-5-20250929_16K

https://htihle.github.io/weirdml.html · external

Run: Date not supplied · weirdml_external.csv

Reported standard error: ±0.01 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
WeirdMLCoding
46.70%

claude-sonnet-4-5-20250929

https://htihle.github.io/weirdml.html · external

Run: Date not supplied · weirdml_external.csv

Reported standard error: ±0.01 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
13.61%

claude-sonnet-4-5-20250929_32K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
6.94%

claude-sonnet-4-5-20250929_16K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
6.94%

claude-sonnet-4-5-20250929_8K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
5.83%

claude-sonnet-4-5-20250929_1K

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
3.75%

claude-sonnet-4-5-20250929

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
HLEKnowledge
13.72%

claude-sonnet-4-5-20250929_unknown

External result; evaluator not specified · external

Run: Date not supplied · hle_external.csv

Reported standard error: ±1.35 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
HLEKnowledge
7.52%

claude-sonnet-4-5-20250929_unknown

External result; evaluator not specified · external

Run: Date not supplied · hle_external.csv

Reported standard error: ±1.03 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
CritPtOther
1.14%

claude-sonnet-4-5-20250929_unknown

External result; evaluator not specified · external

Run: Date not supplied · critpt_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
Remote Labor IndexAgents
2.08%

claude-sonnet-4-5-20250929_unknown

External result; evaluator not specified · external

Run: Date not supplied · rli_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
GDPvalAgents
42.50%

claude-sonnet-4-5-20250929

External result; evaluator not specified · external

Run: Date not supplied · gdpval_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
METR Time HorizonsOther
67.38%

claude-sonnet-4-5-20250929_16K

METR - Measuring AI Ability to Complete Long Tasks · external

Run: Date not supplied · metr_time_horizons_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ProofBenchReasoning
19.00%

claude-sonnet-4-5-20250929_unknown

https://www.vals.ai/benchmarks/proof_bench · external

Run: Date not supplied · proofbench_external.csv

Reported standard error: ±3.92 pp. This is not a 90% interval.

ProofBench v1.0-era value; model absent from the v1.1 board (vals.ai re-grade 2026-08-14, methodology changed) and not re-run. Not comparable to v1.1 rows. Annotated 2026-08-18.

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
LMCAReasoning
38.76%

claude-sonnet-4-5-20250929_unknown

https://conceptualreasoning.ai/lmca · external

Run: Date not supplied · lmca_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
DTBenchReasoning
83.20%

claude-sonnet-4-5-20250929_unknown

https://conceptualreasoning.ai/dtbench · external

Run: Date not supplied · dtbench_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
EnigmaEvalOther
6.00%

claude-sonnet-4-5-20250929_unknown

https://labs.scale.com/leaderboard/enigma_eval · external

Run: Date not supplied · enigma_eval_external.csv

Reported standard error: ±1.35 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗

DC Score v3 / independent source families

One fixed panel. Every weight visible.

DC Power is our weighted aggregate of raw benchmark scores from LiveBench, Epoch AI, ARC Prize and Terminal-Bench. It is not an ECI rescaling. Power = 0.35 × Coding + 0.35 × Reasoning + 0.30 × Agents. These are explicit editorial preferences, not statistically learned weights or a probability of success.

DomainPower weightSource panels within the domain
Coding35%

50% LiveBench 2 Coding · 25 Oct 2026

50% Epoch AI original MirrorCode

Reasoning35%

40% LiveBench 2 Reasoning · 25 Oct 2026

30% Epoch AI original reasoning panel

30% ARC Prize · ARC-AGI-2 semi-private

Agents30%

50% LiveBench 2 Long Agentic · 25 Oct 2026

50% Terminal-Bench 4.0 · published model + agent

Source balance. At full coverage, LiveBench contributes 46.5%, original Epoch AI runs 28%, ARC Prize 10.5% and Terminal-Bench 15%. One source does not gain weight by publishing more rows. ECI, vendor reports and external scores republished through Epoch have zero Power weight. Direct ARC and Terminal results enter once.

Epoch reasoning panel. Equal weights for original Epoch-run Chess Puzzles, FrontierMath tiers 1–3 v2 private and OTIS Mock AIME 2024–2025. All three are required. GPQA and other supplementary tests stay in the matrix; vendor-only GPQA reports do not become independent Epoch runs.

Missing evidence stays visible. Power, Eco and Overall require every fixed source panel. Domain scores can show a partial summary: available panel weights are renormalized, with coverage and missing inputs shown. A partial score is not a win against a complete score. The same complete panel is required for every ranked model.

Fixed editions and effort policy. LiveBench 2 edition 25 October 2026 and Terminal-Bench 4.0. Select known effort in this order: max, xhigh, high, medium, low, minimal, none, declared highest-supported. Never select the largest numerical result. A dated later run can replace an earlier run under the same setup; unresolved conflicts or different harnesses are missing.

Publisher independence is limited. Four separate source organizations do not imply blind or independently reproduced runs, independent funding, equal compute budgets or uncorrelated tests. Terminal-Bench measures a model with its published agent; Claude Code, Codex and other harnesses differ. Inspect the selected configurations. Public benchmark data cannot establish outcomes in your application.

No invented confidence interval. We do not convert ECI uncertainty into uncertainty for this aggregate. No statistically valid DC Power interval is available. Raw means are averaged on their original 0–100 scales; test difficulty and contamination can affect results. A small aggregate difference is descriptive, not proof of superiority.

Token cost C = (3,000 × input rate + 1,000 × output rate) / 1,000,000, uncached. DC Eco = Power / (1 + 100 × C), eligible only for complete Power ≥ 50 and known prices. At $0.01, Eco is half Power. DC Overall = 0.75 × Power + 0.25 × Eco. Use the comparison calculator for your workload and quality weight.

Cost is conditional. Prices are listed USD per million tokens. Reasoning tokens, tools, retries, cache writes, discounts and long-context surcharges are excluded. These are token-spend estimates, not measured cost per successful task. Quality benchmark effort does not establish a matching token workload.

Inspect Claude Fable 5.1: weights, inputs & missing evidence

Fixed-panel coverage: 100%. All ranked models use this complete panel. ECI contributes 0%.

Coding: 85.5 · 35% of Power · 100% coverage

LiveBench 2 Coding · 25 Oct 2026 · 50% of Coding = 17.5% of Power · 97.7

LiveBench 2 Coding · 20261025: 97.70% ↗claude-fable-5.1 · max · LiveBench 2 20261025 · LiveBench 2 · 20261025 · LiveBench

Epoch AI original MirrorCode · 50% of Coding = 17.5% of Power · 73.3

MirrorCode: 73.30% ↗claude-fable-5-1_high · Epoch Inspect · Epoch AI evaluation

Reasoning: 87.5 · 35% of Power · 100% coverage

LiveBench 2 Reasoning · 25 Oct 2026 · 40% of Reasoning = 14.0% of Power · 91.7

LiveBench 2 Reasoning · 20261025: 91.70% ↗claude-fable-5.1 · max · LiveBench 2 20261025 · LiveBench 2 · 20261025 · LiveBench

Epoch AI original reasoning panel · 30% of Reasoning = 10.5% of Power · 79.4

Chess Puzzles: 48.00% ↗claude-fable-5-1_max · Epoch Inspect · Epoch AI evaluation · each input 33.33% of this panel

FrontierMath-Tiers-1-3-v2-Private: 90.18% ↗claude-fable-5-1_max · Epoch Inspect · Epoch AI evaluation · each input 33.33% of this panel

OTIS Mock AIME 2024-2025: 100.00% ↗claude-fable-5-1_max · Epoch Inspect · Epoch AI evaluation · each input 33.33% of this panel

ARC Prize · ARC-AGI-2 semi-private · 30% of Reasoning = 10.5% of Power · 90.0

ARC-AGI-2 · semi-private: 90.00% ↗Claude Fable 5.1 (Max) · ARC Prize leaderboard baseline · ARC Prize official leaderboard

Agents: 67.9 · 30% of Power · 100% coverage

LiveBench 2 Long Agentic · 25 Oct 2026 · 50% of Agents = 15.0% of Power · 77.9

LiveBench 2 Long Agentic · 20261025: 77.90% ↗claude-fable-5.1 · max · LiveBench 2 20261025 · LiveBench 2 · 20261025 · LiveBench

Terminal-Bench 4.0 · published model + agent · 50% of Agents = 15.0% of Power · 57.9

Terminal-Bench 4.0: 57.88% ↗Claude Fable 5.1 · Claude Code · max · Terminal-Bench 4.0 · Claude Code · Terminal-Bench public leaderboard

Power = 0.35 × 85.5 + 0.35 × 87.5 + 0.30 × 67.9 = 80.9. Full precision is used before final rounding.

Reference token cost: $0.08 · Eco: 9.0 · Overall: 62.9

v3 replaces the previous ECI transform; scores across methodology versions are not directly comparable. Data refreshes every six hours, not on each page view. Benchmark editions are pinned for comparability; changing the test panel requires a methodology revision. Imports older than 24 hours are marked delayed. Catalogue releases continue to update independently. Azure listings do not confirm account quota or regional capacity.

OpenRouter catalogue ↗ · Public catalogue API; attributed metadata and list prices

models.dev ↗ · MIT

Epoch AI, Capabilities & benchmarking ↗ · CC BY 4.0; only original Epoch-run panel observations enter Power; ECI has zero weight

ARC Prize official leaderboard ↗ · Attributed public leaderboard facts; semi-private split; one direct Power panel, never counted through Epoch again

LiveBench 2 · 25 October 2026 ↗ · Attributed public score facts; original Coding, Reasoning and Long Agentic suites

Terminal-Bench 4.0 ↗ · Attributed public score facts; published model plus agent, not a model-only ablation

Microsoft Azure Retail Prices ↗ · Public retail meters; deployment eligibility is not confirmed

Epoch data: CC BY 4.0. Other publishers: attributed public leaderboard score facts. DARC.DEV defines the aggregate and makes no claim of source endorsement. No private account details are published.

← Back to DC Model Index