evals.report
BenchmarksLabsCompareRun guidesIn the wild
evals.report·v0.1ReferenceBuilt by inductive.ml

LLM eval scores with sources, run context, and caveats attached.

Track official benchmark scores, vendor-reported model launches, and clearly labeled community runs — each kept with its source, run context, and caveats. No composite ranking. No fake “best model.” Just the receipt.

⌘K
82 benchmarks·134 models·33 labs·Data snapshot 2026·07·15

Index 04

Benchmarks 06

See all
01
SWE-bench VerifiedCoding/% resolved/↑ higher

A curated SWE-bench split for evaluating systems that resolve real software engineering issues.

github.com/SWE-bench/SWE-bench56 reportedguide available
95.0%
Top reported · Claude Fable 5
02
Terminal-Bench 2.1Agents/task success/↑ higher

A command-line agent benchmark for completing terminal tasks in reproducible task environments.

github.com/laude-institute/terminal-bench29 reportedguide available
91.9%
Top reported · GPT-5.6 Sol Ultra
03
DeepSWECoding/% resolved/↑ higher

A long-horizon software-engineering benchmark with original tasks, broad repository coverage, and behavioral verifiers.

github.com/datacurve-ai/deep-swe20 reportedguide available
70.05%
Top reported · GPT-5.5
04
SWE-bench ProCoding/% resolved/↑ higher

A harder public software-engineering agent benchmark built around professional repository tasks.

github.com/scaleapi/SWE-bench_Pro-os50 reportedguide available
80.0%
Top reported · Claude Fable 5
05
Humanity's Last ExamReasoning/accuracy/↑ higher

A broad expert-level academic question-answering benchmark for frontier reasoning systems.

47 reportedguide available
56.8%
Top reported · Claude Mythos Preview
06
GDPvalAgents/Elo/↑ higher

GDPval evaluates AI models agentically (shell + web access via a sandbox harness) on real-world economically valuable knowledge-work deliverables — documents, spreadsheets, slides, diagrams — spanning 44 occupations across 9 major U.S. GDP industries, scored by blind pairwise quality comparison; the Artificial Analysis GDPval-AA variant reports results as an Elo rating.

huggingface.co/datasets/openai/gdpval70 reported
1932
Top reported · Claude Fable 5

Compare

Open
BenchmarkGPT-5.5OpenAIClaude Opus 4.8AnthropicGemini 3.1 Pro PreviewGoogle DeepMindDeepSeek V4 ProDeepSeek
SWE-bench Verified% resolved80.6%88.6%75.6%80.6%
DeepSWE% resolved70.05%58%9.88%5.3%
SWE-bench Pro% resolved58.6%69.2%46.10%55.4%

Run guides 04

All guides