Developer

Integration test generation

Generate integration tests with setup/teardown and stable fixtures.

task.test_generation_integration

Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

claude-sonnet-4

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

29.0%

Best benchmark score

39.8%

Confidence

All ranked models — top 3

🥇

claude-sonnet-4

29.0%

🥈

gpt-5-2025-08-07

27.0%

🥉

gpt-4o-2024-05-13

23.0%

Ranked Models

Evidence Quality

81%

Evidence Points

Top Signal

SWE-bench Verified Leaderboard: swe_verified_resolved_pct

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥈	claude-sonnet-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	29.0%	40%	$6.00	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
🥉	gpt-5-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	27.0%	32%	—	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#4	gpt-4o-2024-05-13 Strong on RepoQA Official Results overall_average_pass_at_1_pct and BigCodeBench Official bigcodebench_complete_pct	23.0%	31%	—	RepoQA Official ResultsBigCodeBench Official
#5	gpt-4o-20241120 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	22.1%	37%	—	BigCodeBench OfficialBigCodeBench Official
#7	o3-20250416 Strong on Aider Polyglot Leaderboard percent_correct_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct	20.8%	27%	$3.50	Aider Polyglot LeaderboardSWE-bench Verified Leaderboard
#9	Kimi K2 Thinking Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Sonar Java Quality Leaderboard functional_skill_pct	19.8%	28%	$1.07	SWE-bench Verified LeaderboardSonar Java Quality Leaderboard
#10	gemini-3-pro-preview Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals SWE-bench overall_accuracy_pct	19.2%	23%	$4.50	SWE-bench Verified LeaderboardVals SWE-bench
#11	deepseek-r1 Strong on Aider Polyglot Leaderboard percent_correct_pct and Sonar Java Quality Leaderboard functional_skill_pct	19.0%	26%	$0.27	Aider Polyglot LeaderboardSonar Java Quality Leaderboard
#12	gpt-5.2-2025-12-11 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals SWE-bench overall_accuracy_pct	18.7%	22%	—	SWE-bench Verified LeaderboardVals SWE-bench
#13	gpt-4.1-20250414 Strong on Galileo Agent Leaderboard v2 Avg AC and SWE-bench Verified Leaderboard swe_verified_resolved_pct	18.0%	29%	—	Galileo Agent Leaderboard v2SWE-bench Verified Leaderboard
#14	gemini-2.5-pro Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Galileo Agent Leaderboard v2 Avg AC	17.8%	26%	$3.44	SWE-bench Verified LeaderboardGalileo Agent Leaderboard v2
#17	claude-opus-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	17.5%	21%	$10.00	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#18	qwen-2.5-72b-instruct Strong on BigCodeBench Official bigcodebench_complete_pct and Galileo Agent Leaderboard v2 Avg AC	17.2%	23%	—	BigCodeBench OfficialGalileo Agent Leaderboard v2
#19	o4-mini Strong on Aider Polyglot Leaderboard percent_correct_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct	17.0%	26%	$1.93	Aider Polyglot LeaderboardSWE-bench Verified Leaderboard
#22	gpt-4.1 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	16.6%	19%	$3.50	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#24	gpt-5-mini-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals LiveCodeBench overall_accuracy_pct	16.1%	24%	—	SWE-bench Verified LeaderboardVals LiveCodeBench
#26	claude-opus-4-5-20251101 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Terminal-Bench 2 overall_accuracy_pct	15.7%	19%	—	SWE-bench Verified LeaderboardVals Terminal-Bench 2
#29	glm-4.7 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Vals LiveCodeBench overall_accuracy_pct	14.6%	21%	—	Sonar Java Quality LeaderboardVals LiveCodeBench
#30	gemini-3.1-pro-preview Strong on Vals SWE-bench overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	14.5%	15%	$4.50	Vals SWE-benchVals LiveCodeBench
#32	minimax-m2.1 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Vals SWE-bench overall_accuracy_pct	14.1%	21%	$0.53	Sonar Java Quality LeaderboardVals SWE-bench
#34	deepseek-v3 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	13.7%	17%	—	BigCodeBench OfficialBigCodeBench Official
#35	Grok-4-0709 Strong on Vals LiveCodeBench overall_accuracy_pct and Galileo Agent Leaderboard v2 Avg AC	13.5%	21%	—	Vals LiveCodeBenchGalileo Agent Leaderboard v2
#38	gpt-4o-2024-08-06 Strong on BigCodeBench Official bigcodebench_hard_complete_pct and Aider Code Editing Leaderboard percent_correct_pct	13.0%	23%	—	BigCodeBench OfficialAider Code Editing Leaderboard
#39	gpt-4o Strong on Sonar Java Quality Leaderboard functional_skill_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct	12.4%	26%	$0.26	Sonar Java Quality LeaderboardSWE-bench Verified Leaderboard
#40	gpt-4o-mini-2024-07-18 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	12.4%	20%	—	BigCodeBench OfficialBigCodeBench Official
#41	Llama 3.3 70B Instruct Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	12.2%	22%	—	BigCodeBench OfficialBigCodeBench Official
#42	gemini-3-flash-preview Strong on Vals SWE-bench overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	12.2%	15%	$1.13	Vals SWE-benchVals LiveCodeBench
#43	gpt-5.4-2026-03-05 Strong on Vals SWE-bench overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	12.1%	14%	—	Vals SWE-benchVals LiveCodeBench
#44	claude-sonnet-4.6 Strong on Vals SWE-bench overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	11.8%	14%	$6.00	Vals SWE-benchVals LiveCodeBench
#46	claude-opus-4-6-thinking Strong on Vals SWE-bench overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	11.6%	13%	—	Vals SWE-benchVals LiveCodeBench

Compare Models

Select two different models above to compare their evidence side by side.

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

Vals LiveCodeBench

38 rows · 1.0% avg lift

Vals Legal Bench

36 rows · 0.2% avg lift

Vals Tax Eval v2

36 rows · 0.2% avg lift

Vals MedQA

33 rows · 0.2% avg lift

Missing frontier models

No obvious gaps right now.

▶Taxonomy & task details

Core tasks

task.test_generation_integration

Required modes

none

Domains

domain.software_engineering

Related in Developer

Codebase onboarding brief

Summarize a repository's architecture, modules, and conventions.

Autonomous Coding Agent

End-to-end autonomous software engineering: reading issues, writing code, running tests, submitting PRs.

Code generation

Generate correct, secure code from requirements.

Refactoring assistant

Refactor code safely while preserving behavior and improving clarity.