JumalAIta IntelligenceIndependent evaluation

Benchmarks / Model

Claude Opus 4.7

Results for Claude Opus 4.7 by Anthropic across JumalAIta Intelligence benchmarks, with the configuration and run details of every evaluation.

01 / Result

Creative Reimplementation Benchmark

Anthropic · Single shot · High reasoning

Benchmark version
v1.0
Generation
Single shot
Reasoning effort
High
Harness
Claude Code
Run date
2026-08-09
Run environment
Not yet published
Run time
26 min 28 s
Tool calls
48
Cost
Not yet published
Tokens
Not yet published
Evaluators
The original authors of the reference demo (members of Jumalauta)
Recording length
2 min 55 s
Recording published
2026-09-06

Evaluators' notes

  1. According to the original authors, the Claude Opus 4.7 version looks noticeably rougher than the Claude Fable 5.1 and GPT-6 Astra entries.

02 / Summary

Benchmark results

Results for Claude Opus 4.7, one row per benchmark.
BenchmarkVersionRankEvaluationConfigurationStatusResult
Creative Reimplementation Benchmarkv1.08Expert-rankedSingle shot · HighFinalDetails of Claude Opus 4.7 in Creative Reimplementation Benchmark
Organization
Anthropic
Benchmarks
1