Developer

Code generation

Generate correct, secure code from requirements.

task.code_generationtask.api_usage_correctness

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

Provisional leader

claude-opus-4-6

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

26.6%

Best benchmark score

29.3%

Confidence

All ranked models — top 3

🥇

claude-opus-4-6

26.6%

🥈

gpt-5-2025-08-07

24.4%

🥉

claude-sonnet-4

22.2%

Ranked Models

Evidence Quality

82%

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-opus-4-6 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and OpenHands Issue Resolution issue_resolution_score_pct	26.6%	29%	$10.00	SWE-bench Verified LeaderboardOpenHands Issue Resolution
🥈	gpt-5-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	24.4%	28%	—	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#4	claude-sonnet-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Sonar Java Quality Leaderboard functional_skill_pct	22.2%	31%	$6.00	SWE-bench Verified LeaderboardSonar Java Quality Leaderboard
#7	GLM-5 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Sonar Java Quality Leaderboard issue_density_error_per_kloc	19.8%	32%	—	Sonar Java Quality LeaderboardSonar Java Quality Leaderboard
#9	Kimi K2 Thinking Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Sonar Java Quality Leaderboard functional_skill_pct	19.0%	44%	$1.07	SWE-bench Verified LeaderboardSonar Java Quality Leaderboard
#12	claude-sonnet-4.6 Strong on OpenHands Issue Resolution issue_resolution_score_pct and OpenHands Index issue_resolution_score_pct	17.2%	30%	$6.00	OpenHands Issue ResolutionOpenHands Index
#13	gpt-4o-2024-05-13 Strong on RepoQA Official Results overall_average_pass_at_1_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct	16.3%	22%	—	RepoQA Official ResultsSWE-bench Verified Leaderboard
#14	gemini-3-pro-preview Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and AppBench Leaderboard percentile_score_pct	15.4%	19%	$4.50	SWE-bench Verified LeaderboardAppBench Leaderboard
#17	o3-20250416 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	14.4%	19%	$3.50	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#19	deepseek-r1 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Aider Polyglot Leaderboard percent_correct_pct	14.3%	20%	$0.27	Sonar Java Quality LeaderboardAider Polyglot Leaderboard
#20	gpt-4o-20241120 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	14.3%	25%	—	BigCodeBench OfficialBigCodeBench Official
#21	minimax-m2.1 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Vals SWE-bench overall_accuracy_pct	13.8%	38%	$0.53	Sonar Java Quality LeaderboardVals SWE-bench
#22	gpt-5.2-2025-12-11 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals SWE-bench overall_accuracy_pct	13.4%	16%	—	SWE-bench Verified LeaderboardVals SWE-bench
#23	gemini-2.5-pro Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Galileo Agent Leaderboard v2 Avg AC	13.0%	18%	$3.44	SWE-bench Verified LeaderboardGalileo Agent Leaderboard v2
#25	claude-opus-4 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	12.6%	15%	$10.00	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#26	kimi-k2.5-thinking Strong on Vals LiveCodeBench overall_accuracy_pct and Vals SWE-bench overall_accuracy_pct	12.3%	29%	—	Vals LiveCodeBenchVals SWE-bench
#27	gpt-4.1 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	12.2%	14%	$3.50	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#28	gpt-4.1-20250414 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Galileo Agent Leaderboard v2 Avg AC	12.1%	20%	—	SWE-bench Verified LeaderboardGalileo Agent Leaderboard v2
#30	claude-opus-4-5-20251101 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals Terminal-Bench 2 overall_accuracy_pct	11.8%	14%	—	SWE-bench Verified LeaderboardVals Terminal-Bench 2
#31	o4-mini Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Aider Polyglot Leaderboard percent_correct_pct	11.7%	18%	$1.93	SWE-bench Verified LeaderboardAider Polyglot Leaderboard
#32	glm-4.7 Strong on Sonar Java Quality Leaderboard functional_skill_pct and Sonar Java Quality Leaderboard issue_density_error_per_kloc	11.6%	17%	—	Sonar Java Quality LeaderboardSonar Java Quality Leaderboard
#35	gpt-5-mini-2025-08-07 Strong on SWE-bench Verified Leaderboard swe_verified_resolved_pct and Vals LiveCodeBench overall_accuracy_pct	11.4%	17%	—	SWE-bench Verified LeaderboardVals LiveCodeBench
#37	qwen-2.5-72b-instruct Strong on BigCodeBench Official bigcodebench_complete_pct and Galileo Agent Leaderboard v2 Avg AC	10.7%	14%	—	BigCodeBench OfficialGalileo Agent Leaderboard v2
#42	gpt-4o Strong on Sonar Java Quality Leaderboard functional_skill_pct and SWE-bench Verified Leaderboard swe_verified_resolved_pct	9.8%	22%	$0.26	Sonar Java Quality LeaderboardSWE-bench Verified Leaderboard
#47	gpt-4o-2024-08-06 Strong on BigCodeBench Official bigcodebench_hard_complete_pct and Aider Code Editing Leaderboard percent_correct_pct	9.3%	18%	—	BigCodeBench OfficialAider Code Editing Leaderboard
#51	deepseek-v3 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	8.5%	11%	—	BigCodeBench OfficialBigCodeBench Official
#52	Grok-4-0709 Strong on Vals LiveCodeBench overall_accuracy_pct and Galileo Agent Leaderboard v2 Avg AC	8.3%	13%	—	Vals LiveCodeBenchGalileo Agent Leaderboard v2
#56	gpt-4o-mini-2024-07-18 Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	7.8%	16%	—	BigCodeBench OfficialBigCodeBench Official
#57	Llama 3.3 70B Instruct Strong on BigCodeBench Official bigcodebench_complete_pct and BigCodeBench Official bigcodebench_instruct_pct	7.6%	13%	—	BigCodeBench OfficialBigCodeBench Official
#58	Phi-3-medium-128k-instruct Strong on RepoQA Official Results overall_average_pass_at_1_pct and BigCodeBench Official bigcodebench_complete_pct	7.4%	11%	—	RepoQA Official ResultsBigCodeBench Official

Compare Models

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

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

SWE-bench Verified Leaderboard

19 rows · 3.1% avg lift

Vals LiveCodeBench

19 rows · 0.9% avg lift

Vals MedQA

15 rows · 0.2% avg lift

Vals Legal Bench

14 rows · 0.2% avg lift

Missing frontier models

grok-4-1-fast-reasoning

Thin evidence after weighting

Rank #12

19.5%

grok-4-1-fast-non-reasoning

Thin evidence after weighting

Rank #15

14.9%

▶Taxonomy & task details

Core tasks

task.code_generationtask.api_usage_correctness

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.

Refactoring assistant

Refactor code safely while preserving behavior and improving clarity.

IDE code completion

Fast local-context code completion and small snippet generation.