Claude Opus 4

Claude Opus 4 is Anthropic's most powerful model yet and the state-of-the-art coding model. It delivers sustained performance on long-running tasks that require focused effort and thousands of steps,…

vercelAIGatewayCatalog/anthropic/claude-opus-4

Claude Opus 4 is Anthropic's most powerful model yet and the state-of-the-art coding model. It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, significantly expanding what AI agents can solve. Claude Opus 4 is ideal for powering frontier agent products and features.

Specifications & capabilities

Input
text, image, pdf
Output
text
Context window · tokens
200000
Max output · tokens
32000

Evaluations

1–5 / 5

HELM Capabilities

85.9%

source id
helm
leaderboard name
HELM MMLU-Pro
dimension
intelligence
metric
chain_of_thought_correctness
rank
6
sample size
1000
source model id
anthropic/claude-opus-4-20250514
Original result ↗

HELM Capabilities

91.774%

source id
helm
leaderboard name
HELM IFEval
dimension
agentic
metric
ifeval_strict_accuracy
rank
7
sample size
541
source model id
anthropic/claude-opus-4-20250514
Original result ↗

HELM Capabilities

66.592%

source id
helm
leaderboard name
HELM GPQA
dimension
intelligence
metric
chain_of_thought_correctness
rank
15
sample size
446
source model id
anthropic/claude-opus-4-20250514
Original result ↗

HELM Capabilities

83.3%

source id
helm
leaderboard name
HELM WildBench
dimension
agentic
metric
wildbench_score_rescaled
rank
18
sample size
1000
source model id
anthropic/claude-opus-4-20250514
Original result ↗

HELM Capabilities

51.117%

source id
helm
leaderboard name
HELM Omni-MATH
dimension
intelligence
metric
omni_math_accuracy
rank
18
sample size
1000
source model id
anthropic/claude-opus-4-20250514
Original result ↗

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

46 / 100

source id
stanfordFMTI
canonical model id
vercelAIGatewayCatalog/anthropic/claude-opus-4
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Anthropic
assessment type
organization-level disclosure
metric
disclosure_score
result label
46 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–3 / 3

Epoch AI · Catalog ↗

GitHub · Catalog ↗

crfm.stanford.edu · Catalog ↗

Source links

1–3 / 3

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace