LLM Benchmark Results & Evaluator Comparisons
Browse selected source-linked LLM benchmark tables, with vendor scores and independent evaluator measurements kept separate.
These 15 tables have recorded results and descriptive context. The full interactive library includes every tracked metric, including sparse and missing results.
DeepSWE v1.1
Long-horizon agentic software engineering on original tasks from active open-source repos (Datacurve DeepSWE).
26 / 30 models with results →Official / vendorAutomationBench v1.0.6
General agent automation across multi-step workflows (forms, apps, scripts) rather than pure coding.
18 / 30 models with results →Official / vendorTerminal-Bench 2.1
Earlier Terminal-Bench agent suite (shorter/earlier protocol than 3.0/4.0); keep separate from later versions.
17 / 30 models with results →Official / vendorGPQA Diamond
Graduate-level science QA
15 / 30 models with results →Official / vendorTerminal-Bench 4.0
Multi-hour agentic terminal/coding tasks: shell, tools, and long-running project work under a hard time budget.
15 / 30 models with results →Official / vendorAgents' Last Exam
Hard multi-step agent exam stressing planning, tools, and failure recovery at the frontier.
14 / 30 models with results →Official / vendorOSWorld 2.0
Computer-use / desktop agent: operate a real GUI environment to complete open-ended tasks (partial scores must be noted).
14 / 30 models with results →Official / vendorSWE-bench Pro
Long-horizon software engineering on real GitHub issues beyond the classic SWE-bench Verified set.
12 / 30 models with results →Official / vendorHealthBench Professional
OpenAI HealthBench Professional: evaluates model capability and safety on real clinician-oriented chats (copilot-style medical professional use), graded with physician rubrics. Distinct from HealthBench Hard (hardest consumer/health conversation subset).
11 / 30 models with results →Official / vendorJobBench
Job/task agent benchmark
11 / 30 models with results →Official / vendorGDPval-AA v2
GDPval-AA knowledge-work Elo (v2 as reported)
10 / 30 models with results →IndependentIntelligence Index · Artificial Analysis
Recorded Intelligence Index measurements from Artificial Analysis, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.
22 / 30 models with results →IndependentVals Index · Vals AI
Recorded Vals Index measurements from Vals AI, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.
21 / 30 models with results →IndependentBugs fixed /105 · Bug Hunt Bench
Recorded Bugs fixed /105 measurements from Bug Hunt Bench, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.
20 / 30 models with results →IndependentARC-AGI-2 · ARC Prize
Recorded ARC-AGI-2 measurements from ARC Prize, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.
10 / 30 models with results →