LLM

Claude Opus 4.7 (Non-reasoning, High Effort)

Name: Claude Opus 4.7 (Non-reasoning, High Effort) Review & Benchmarks
Item: Claude Opus 4.7 (Non-reasoning, High Effort)
Rating: 42.7
Author: Sentient Weekly

by Anthropic

Overall Score

42.7

Anthropic's flagship reasoning model

Released Apr 2026

Benchmark Scores

Reasoning

—

Coding

73.6

Math

—

Creative writing

—

Instruction following

—

Multimodal

—

Standard Benchmarks

aa_lcraa_lcr

0.7

Measured 2026-06-28 · source

aa_terminalbench_hardaa_terminalbench_hard

0.6

Measured 2026-06-28 · source

aa_terminalbench_v2_1aa_terminalbench_v2_1

0.8

Measured 2026-06-28 · source

aa_tau_bankingaa_tau_banking

0.3

Measured 2026-06-28 · source

aa_gpqaaa_gpqa

0.9

Measured 2026-06-28 · source

aa_hleaa_hle

0.3

Measured 2026-06-28 · source

aa_scicodeaa_scicode

0.5

Measured 2026-06-28 · source

aa_ifbenchaa_ifbench

0.4

Measured 2026-06-28 · source

aa_tau2aa_tau2

0.7

Measured 2026-06-28 · source

Price

$15 / 1M input · $75 / 1M output

Paid

Context

1M tokens

Speed

43.5 t/s

23704ms TTFT

Compare this model →

Overview

Anthropic's flagship reasoning model. Excellent at complex multi-step analysis, long-context retrieval, agentic workflows, and producing high-quality writing. The 1M-token context window enables full-codebase or full-document workflows.

Strengths

State-of-the-art reasoning · 1M-token context · best-in-class agentic tool use · strong creative writing · careful, calibrated answers

Known limitations

Higher cost per token than smaller models · slightly slower than Sonnet · still has some refusal/over-cautiousness on legitimate edge cases

Discussion

0 comments

Be the first to comment.