BasedAGIBasedAGI
Menu
Rankings live

developer_tools

IDE code completion

Fast local-context code completion and small snippet generation.

#1 Recommendation

anthropic/claude-sonnet-4.6

Strong on OpenHands Index greenfield_score_pct (75%) and OpenHands Issue Resolution issue_resolution_score_pct (72%)

external/anthropic/claude-sonnet-4-6

21.3%

Score

37.8%

Confidence

Limited benchmark evidence for this use case.

38 ranked models with average evidence of 15.7 points. Rankings may shift as more benchmark data is ingested.

Ranked Models

30

Evidence Quality

80%

Scoring

Benchmark-backed

Top Signal

OpenHands Index: greenfield_score_pct

All Ranked Models

Max params:
Min confidence:
30 of 30
RankModelScore
#5anthropic/claude-sonnet-4.6
21.3%
#8kimi/kimi-k2.5-thinking
17.9%
#11minimax/minimax-m2.1
16.6%
#12Kimi K2 Thinking
16.2%
#15deepseek/deepseek-r1
14.0%
#16z-ai/glm-4.7
13.4%
#17gemini-3-pro-preview
12.8%
#18google/gemini-3.1-pro-preview
11.5%
#19Grok-4-0709
11.4%
#20gpt-4o-2024-08-06
11.3%
#21gpt-4.1-20250414
11.0%
#22claude-sonnet-4-20250514
10.9%
#23openai/gpt-5.4-2026-03-05
10.8%
#25anthropic/claude-opus-4-6-thinking
10.4%
#26claude-opus-4-5-20251101
10.3%
#28gemini-3-flash-preview
10.1%
#29gpt-5-2025-08-07
10.1%
#30gpt-5.2-2025-12-11
10.0%
#31gpt-5.1-2025-11-13
10.0%
#32anthropic/claude-opus-4-5-20251101-thinking
9.9%
#34gpt-4o
9.6%
#36gpt-4o-20241120
9.2%
#40anthropic/claude-sonnet-4-5-20250929-thinking
8.8%
#42gemini-2.5-pro
8.5%
#44zai/glm-5-thinking
8.1%
#45qwen-2.5-72b-instruct
8.1%
#47gpt-4o-2024-05-13
8.1%
#48xai-org/grok-4-fast-reasoning
7.9%
#49google/gemini-3.1-flash-lite-preview
7.9%
#52gpt-4.1-mini-20250414
7.7%

Compare Models

Model A leads by +3.4%

Shareable Link →

Model A

anthropic/claude-sonnet-4.6

external/anthropic/claude-sonnet-4-6

21.3%

Rank #5

Confidence 37.8%26 evidence pts

OpenHands Index: greenfield_score_pct

Value 75.2% · Conf 100.0% · Weight 1.8%

openhands_index.greenfield_score_pct (Mar 12, 2026)

OpenHands Issue Resolution: issue_resolution_score_pct

Value 71.8% · Conf 100.0% · Weight 1.8%

openhands_issue_resolution.issue_resolution_score_pct (Mar 12, 2026)

Vals SWE-bench: overall_accuracy_pct

Value 95.1% · Conf 100.0% · Weight 1.8%

vals_swebench.overall_accuracy_pct (Mar 12, 2026)

Vals LiveCodeBench: overall_accuracy_pct

Value 91.2% · Conf 100.0% · Weight 1.5%

vals_lcb.overall_accuracy_pct (Mar 12, 2026)

Model B

kimi/kimi-k2.5-thinking

external/kimi/kimi-k2-5-thinking

17.9%

Rank #8

Confidence 37.6%26 evidence pts

Vals LiveCodeBench: overall_accuracy_pct

Value 93.6% · Conf 100.0% · Weight 1.5%

vals_lcb.overall_accuracy_pct (Mar 12, 2026)

Vals SWE-bench: overall_accuracy_pct

Value 82.6% · Conf 100.0% · Weight 1.5%

vals_swebench.overall_accuracy_pct (Mar 12, 2026)

OpenHands Index: average_score_pct

Value 35.5% · Conf 100.0% · Weight 1.2%

openhands_index.average_score_pct (Mar 12, 2026)

Vals Terminal-Bench 2: overall_accuracy_pct

Value 58.6% · Conf 100.0% · Weight 1.0%

vals_terminal_bench_2.overall_accuracy_pct (Mar 12, 2026)

Ranking Diagnostics & Missing Models

Source Lift

Ranked

38

Sources

8

Quality

Insufficient

Vals LiveCodeBench

vals_lcb

31 rows

1.3% avg lift

Vals SWE-bench

vals_swebench

29 rows

1.3% avg lift

Vals Legal Bench

vals_legal_bench

29 rows

0.3% avg lift

Vals Terminal-Bench 2

vals_terminal_bench_2

28 rows

0.9% avg lift

Missing Strong Models

gemini-2.5-flash

external/google/gemini-2-5-flash

Rank #12

17.9%

Thin evidence after weighting

x-ai/grok-3

external/x-ai/grok-3

Rank #35

12.1%

Thin evidence after weighting

o3-20250416

external/openai/o3-20250416

Rank #43

11.7%

Thin evidence after weighting

anthropic/claude-opus-4-1-20250805

external/anthropic/claude-opus-4-1-20250805

Rank #48

10.8%

Thin evidence after weighting
Taxonomy Details

Core Tasks

task.code_completiontask.api_usage_correctness

Required Modes

none

Domains

domain.software_engineering

Related Use Cases