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 4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

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

anthropic · Released 2026-02-17

Claude Sonnet 4.6
—

DC Power

10.5% fixed panel · Power withheld
—

DC Eco

—

DC Overall

Coding

—

0% · partial

Reasoning

58.3

30% · partial

Agents

—

0% · partial

1M context · $3 / $15

USD per 1M input / output tokens

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management 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-4.6$3 / $15Not verified / On-demandAccount-specific
Azure ↗claude-sonnet-4-6$3 / $15Not verified / Not verifiedAccount-specific
anthropic ↗claude-sonnet-4-6$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: 152.86 · published 90% interval 151.21–154.68

20 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 4.6 as the comparison reference →
Inspect Claude Sonnet 4.6: weights, inputs & missing evidence

Fixed-panel coverage: 10.5%. 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: 58.3 · 35% of Power · 30% 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 · —

Chess Puzzles: 23.00% ↗claude-sonnet-4-6_max · Epoch Inspect · Epoch AI evaluation · each input 33.33% of this panel

OTIS Mock AIME 2024-2025: 71.11% ↗claude-sonnet-4-6_max · Epoch Inspect · Epoch AI evaluation · each input 33.33% of this panel

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

ARC Prize · ARC-AGI-2 semi-private · 30% of Reasoning = 10.5% of Power · 58.3

ARC-AGI-2 · semi-private: 58.33% ↗Claude Sonnet 4.6 (Max) · ARC Prize leaderboard baseline · ARC Prize official leaderboard

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

26 benchmarks · 43 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-4-6_max

Epoch AI evaluation · epoch-run

Run: 2026-08-06 · gpqa_diamond.csv

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

Inspect source ↗

CC BY 4.0

max / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
83.33%

claude-sonnet-4-6_high

Epoch AI evaluation · epoch-run

Run: 2026-07-13 · gpqa_diamond.csv

Reported standard error: ±2.66 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

high / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
83.33%

claude-sonnet-4-6_medium

Epoch AI evaluation · epoch-run

Run: 2026-07-13 · gpqa_diamond.csv

Reported standard error: ±2.66 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

medium / Epoch InspectEpoch AI run ↗
GPQA diamondKnowledge
87.37%

claude-sonnet-4-6_32K

Epoch AI evaluation · epoch-run

Run: 2026-02-20 · gpqa_diamond.csv

Reported standard error: ±2.00 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
FrontierMath-2025-02-28-PrivateReasoning
32.40%

claude-sonnet-4-6_16K

Epoch AI evaluation · epoch-run

Run: 2026-02-20 · frontiermath.csv

Reported standard error: ±2.81 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
8.30%

claude-sonnet-4-6_16K

Epoch AI evaluation · epoch-run

Run: 2026-02-21 · frontiermath_tier_4.csv

Reported standard error: ±4.00 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-4-6_max

Epoch AI evaluation · epoch-run

Run: 2026-08-06 · otis_mock_aime_2024_2025.csv

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

Inspect source ↗

CC BY 4.0

max / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
75.56%

claude-sonnet-4-6_high

Epoch AI evaluation · epoch-run

Run: 2026-07-13 · otis_mock_aime_2024_2025.csv

Reported standard error: ±6.48 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

high / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
82.22%

claude-sonnet-4-6_medium

Epoch AI evaluation · epoch-run

Run: 2026-07-13 · otis_mock_aime_2024_2025.csv

Reported standard error: ±5.76 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

medium / Epoch InspectEpoch AI run ↗
OTIS Mock AIME 2024-2025Reasoning
85.79%

claude-sonnet-4-6_32K

Epoch AI evaluation · epoch-run

Run: 2026-02-20 · otis_mock_aime_2024_2025.csv

Reported standard error: ±4.54 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
SWE-Bench verifiedCoding
75.21%

claude-sonnet-4-6

Epoch AI evaluation · epoch-run

Run: 2026-02-21 · swe_bench_verified.csv

Reported standard error: ±1.96 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
SimpleQA VerifiedKnowledge
32.80%

claude-sonnet-4-6_max

Epoch AI evaluation · epoch-run

Run: 2026-08-27 · simpleqa_verified.csv

Reported standard error: ±1.49 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

max / Epoch InspectEpoch AI run ↗
SimpleQA VerifiedKnowledge
35.50%

claude-sonnet-4-6_high

Epoch AI evaluation · epoch-run

Run: 2026-08-10 · simpleqa_verified.csv

Reported standard error: ±1.51 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

high / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
23.00%

claude-sonnet-4-6_max

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±4.23 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

max / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
19.00%

claude-sonnet-4-6_high

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±3.94 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

high / Epoch InspectEpoch AI run ↗
Chess PuzzlesReasoning
16.00%

claude-sonnet-4-6_medium

Epoch AI evaluation · epoch-run

Run: 2026-10-13 · chess_puzzles.csv

Reported standard error: ±3.68 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

medium / Epoch InspectEpoch AI run ↗
Mystery Game PuzzlesReasoning
14.00%

claude-sonnet-4-6

Epoch AI evaluation · epoch-run

Run: 2026-08-06 · mystery_game_puzzles.csv

Reported standard error: ±3.49 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unspecified / Epoch InspectEpoch AI run ↗
Mystery Game PuzzlesReasoning
16.00%

claude-sonnet-4-6_low

Epoch AI evaluation · epoch-run

Run: 2026-08-06 · mystery_game_puzzles.csv

Reported standard error: ±3.68 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

low / Epoch InspectEpoch AI run ↗
ARC-AGIReasoning
86.50%

claude-sonnet-4-6_high

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

high / Not reportedExternal · via Epoch ↗
ARC-AGIReasoning
86.00%

claude-sonnet-4-6_max

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
DeepResearch BenchAgents
54.90%

claude-sonnet-4-6_high

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

Run: Date not supplied · deepresearchbench_external.csv

Inspect source ↗

CC BY 4.0

high / Not reportedExternal · via Epoch ↗
DeepResearch BenchAgents
50.40%

claude-sonnet-4-6_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 ↗
OSWorldAgents
72.10%

claude-sonnet-4-6

OS World Website · external

Run: Date not supplied · os_world_external.csv

Inspect source ↗

CC BY 4.0

unspecified / claude-sonnet-4-6 (100 steps)External · via Epoch ↗
Terminal BenchCoding
53.43%

claude-sonnet-4-6_unknown

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

Run: 2026-02-17 · terminalbench_external.csv

Reported standard error: ±2.83 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

unknown / Simplai AgentExternal · via Epoch ↗
Terminal BenchCoding
53.40%

claude-sonnet-4-6

External result; evaluator not specified · external

Run: 2026-05-14 · terminalbench_external.csv

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

Inspect source ↗

CC BY 4.0

unspecified / Simplai AgentExternal · via Epoch ↗
WeirdMLCoding
66.07%

claude-sonnet-4-6_medium

WeirdML Leaderboard · external

Run: Date not supplied · weirdml_external.csv

Reported standard error: ±0.03 pp. This is not a 90% interval.

Inspect source ↗

CC BY 4.0

medium / Not reportedExternal · via Epoch ↗
APEX-AgentsAgents
43.00%

claude-sonnet-4-6_high

External result; evaluator not specified · external

Run: Date not supplied · apex_agents_external.csv

Inspect source ↗

CC BY 4.0

high / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
60.42%

claude-sonnet-4-6_high

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

high / Not reportedExternal · via Epoch ↗
ARC-AGI-2Reasoning
58.33%

claude-sonnet-4-6_max

External result; evaluator not specified · external

Run: Date not supplied · arc_agi_2_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
GBAEvalOther
48.76%

claude-sonnet-4-6_unknown

https://gbaeval.com/model/claude-sonnet · external

Run: Date not supplied · gbaeval_external.csv

Inspect source ↗

CC BY 4.0

unknown / Not reportedExternal · via Epoch ↗
CritPtOther
3.14%

claude-sonnet-4-6_max

External result; evaluator not specified · external

Run: Date not supplied · critpt_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
ExploitBenchCoding
23.60%

claude-sonnet-4-6

External result; evaluator not specified · external

Run: Date not supplied · exploitbench_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
ExploitBenchCoding
22.70%

claude-sonnet-4-6

External result; evaluator not specified · external

Run: Date not supplied · exploitbench_external.csv

Inspect source ↗

CC BY 4.0

unspecified / Not reportedExternal · via Epoch ↗
OSWorld 2.0Agents
9.30%

claude-sonnet-4-6_medium

https://osworld-v2.xlang.ai/ · external

Run: Date not supplied · osworld_2_external.csv

Inspect source ↗

CC BY 4.0

medium / Not reportedExternal · via Epoch ↗
OSWorld 2.0Agents
8.30%

claude-sonnet-4-6_max

https://osworld-v2.xlang.ai/ · external

Run: Date not supplied · osworld_2_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
DeepSWECoding
29.93%

claude-sonnet-4-6_high

https://deepswe.datacurve.ai/ · external

Run: Date not supplied · deepswe_external.csv

Inspect source ↗

CC BY 4.0

high / mini-swe-agentExternal · via Epoch ↗
ProofBenchReasoning
45.00%

claude-sonnet-4-6_max

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

Run: Date not supplied · proofbench_external.csv

Reported standard error: ±4.97 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

max / Not reportedExternal · via Epoch ↗
FrontierCodeCoding
24.31%

claude-sonnet-4-6_unknown

https://cognition.com/frontiercode · external

Run: Date not supplied · frontiercode_external.csv

Inspect source ↗

CC BY 4.0

unknown / claude-codeExternal · via Epoch ↗
LMCAReasoning
46.51%

claude-sonnet-4-6_max

https://conceptualreasoning.ai/lmca · external

Run: Date not supplied · lmca_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
DTBenchReasoning
89.87%

claude-sonnet-4-6_max

https://conceptualreasoning.ai/dtbench · external

Run: Date not supplied · dtbench_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
GDP.pdfOther
18.00%

claude-sonnet-4-6_max

https://surgehq.ai/benchmarks/gdp-pdf · external

Run: Date not supplied · gdp_pdf_external.csv

Inspect source ↗

CC BY 4.0

max / Not reportedExternal · via Epoch ↗
ARC-AGI-2 · semi-privateReasoning
58.33%

Claude Sonnet 4.6 (Max)

ARC Prize official leaderboard · benchmark-publisher

Run: Date not supplied · evaluations.json · v2_Semi_Private

Reported benchmark cost: $2.7179 per task. Different from the token-workload estimate.

Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets.

Inspect source ↗

Public leaderboard facts · ARC Prize

max / ARC Prize leaderboard baselineARC Prize ↗
ARC-AGI-2 · semi-privateReasoning
60.42%

Claude Sonnet 4.6 (High)

ARC Prize official leaderboard · benchmark-publisher

Run: Date not supplied · evaluations.json · v2_Semi_Private

Reported benchmark cost: $2.6966 per task. Different from the token-workload estimate.

Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets.

Inspect source ↗

Public leaderboard facts · ARC Prize

high / ARC Prize leaderboard baselineARC Prize ↗

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