Anthropic

Claude Fable 5

Version 5 benchmark runs across the shared Superbash visual prompts.

Official benchmark profile

How Claude Fable 5 scores beyond our visual tests.

Comparable numeric rows from the Anthropic system card and the shared GPT-5.6 comparison table. Marketing-only claims such as ViBench and spreadsheet speedups are excluded unless a score is published.

Anthropic sourceJune 2026Source report →

Coding

SWE-bench Pro

80.0%

Coding

SWE-bench Verified

95.0%

Agentic coding

Terminal-Bench 2.1

84.3%

Full official benchmark table14 rows with source settings and peer charts

Benchmark	Area	Score	Setting / comparison
SWE-bench Pro	Coding	80.0%	Average over 5 trials; standard configuration with thinking blocks included. Claude Fable 580.0% Claude Opus 4.869.2% GPT-5.6 Sol64.6% GPT-5.6 Terra63.4% GPT-5.6 Luna62.7% GPT-5.559.4% Gemini 3.1 Pro54.2%
SWE-bench Verified	Coding	95.0%	Average over 5 trials on the 500-problem verified subset.
Terminal-Bench 2.1	Agentic coding	84.3%	Anthropic mini-SWE-agent harness at high effort; OpenAI’s shared table reports Fable at 83.1%. GPT-5.6 Sol88.8% GPT-5.6 Terra87.4% GPT-5.585.6% GPT-5.6 Luna84.7% Claude Fable 584.3% Claude Opus 4.878.9% Gemini 3.1 Pro70.7%
FrontierCode Diamond	Agentic coding	29.3% score / 30.2% pass	Mean@5 at xhigh reasoning effort on Cognition’s Diamond subset. Claude Fable 529.3% score / 30.2% pass Claude Opus 4.813.4% score / 14.5% pass GPT-5.55.7% score / 6.4% pass
FrontierCode Main	Agentic coding	46.3% score / 48.8% pass	Mean@5 at xhigh reasoning effort on Cognition’s Main subset. Claude Fable 546.3% score / 48.8% pass Claude Opus 4.834.3% score / 37.3% pass GPT-5.525.5% score / 28.2% pass
CursorBench	Agentic coding	72.9%	Cursor production agent harness at maximum effort. Claude Fable 572.9% GPT-5.564.3%
GPQA Diamond	Academic reasoning	92.6%	Shared GPT-5.6 comparison table. GPT-5.6 Sol94.6% Gemini 3.1 Pro94.3% Claude Mythos 594.1% GPT-5.593.6% GPT-5.6 Terra92.9% Claude Fable 592.6% GPT-5.6 Luna92.3% Claude Opus 4.892.0%
FrontierMath Tier 1-3 v2	Math	87.0%	Shared GPT-5.6 comparison table. GPT-5.6 Sol89.0% Claude Fable 587.0% GPT-5.585.3% GPT-5.6 Terra84.9% Claude Opus 4.880.0% GPT-5.6 Luna78.6% Gemini 3.1 Pro59.6%
FrontierMath Tier 4 v2	Math	87.8%	Shared GPT-5.6 comparison table. Claude Fable 587.8% GPT-5.6 Sol83.0% GPT-5.572.5% GPT-5.6 Terra68.3% GPT-5.6 Luna58.5% Claude Opus 4.856.1%
OSWorld-Verified	Computer use	85.0%	Pass@1 averaged over 5 runs on 361 tasks with 100 action steps. Claude Fable 585.0% Claude Opus 4.883.4% GPT-5.578.7% Gemini 3.5 Flash78.4%
Blueprint-Bench 2	Spatial reasoning	38.6%	Andon Labs standard harness; normalized composite floor-plan score. Claude Fable 538.6% GPT-5.536.2% Gemini 3.5 Flash33.6%
OfficeQA Pro	Document reasoning	57.9%	Databricks image-based OfficeQA Pro evaluation. Claude Fable 557.9% GPT-5.552.6% Claude Opus 4.848.1%
Finance Agent Benchmark v2	Finance	56.31%	Vals AI evaluation with adaptive thinking and max effort. Claude Fable 556.31% Claude Opus 4.853.92% GPT-5.551.76%
MCP Atlas	Office work	83.3%	Pass rate on real-world MCP tool-use workflows. Claude Fable 583.3% Claude Opus 4.882.2%