Models / Anthropic

Claude Opus 4.7

Anthropic · Proprietary

Recent snapshotData snapshot cf-1.3
Cheese Index59.0cf-1.3
Input / output$5 / $25USD / 1M tokens
Measured dimensions9 / 13Evidence
Context window1,000,000tokens · conditions unverified

Decision brief

Start by investigating gpqa and swe workloads. These are observed strengths in the dataset; validate them on your own tasks.

Coverage counts measured dimensions, not confidence. Benchmark conditions and public source links may be missing. Missing: Instructions, Multimodal, Multilingual, terminal.

View evidence ↓

Measured task dimensions

Coding
55.1
Agent workflows
54.5
Mathematics
72.9
Knowledge
65.3
Instructions
—
Multimodal
—
Multilingual
—
Reasoning
31.4
swe
87.6
terminal
—
gpqa
94.2
hle
54.7
mcp
77.3

Normalized dimensions. A dash means unknown, not zero.

Input / output

$5 / $25 · USD / 1M tokens

Listed dataset prices; provider terms and dates need verification. Zero without explicit free-price evidence is treated as unknown.

Cache, batch, tool fees and self-hosting costs: not verified.

Index variability stability

100.0 · 7 days of history

band

This is index variability, not API uptime or reliability.

Before deployment

  • Confirm provider endpoint, license and version.
  • Test your prompts, tool calls and failure recovery.
  • Verify prices and latency with real usage.

Evidence

These are source categories published by the dataset. Original public links, sample sizes and harness details remain incomplete.

Source categoryProvenance typeAs ofOriginal public link
Codingcore / official_json2026-11-04Not published
Agent workflowscore / official_json2026-11-04Not published
Long workflowsderived / official_json2026-11-04Not published
arenacross / official_json2026-11-04Not published
depthcore+cross / official_json2026-11-04Not published
Published index inputs · cf-1.3
Coding45.1
Agent workflows54.5
Long workflows63.5
Overall—

The method includes overall, but this snapshot does not expose that input. The total cannot be fully reproduced from these displayed axes.

Method: median of available axes, with an 8% Ops blend when present. Source scores are displayed without recalculation or imputation.

Method →
Index history
As ofCheese Index
2026-10-2959.0
2026-10-3059.0
2026-10-3159.0
2026-11-0159.0
2026-11-0259.0
2026-11-0359.0
2026-11-0459.0

Only recorded dates are shown. Missing days are not filled.