BasedAGIBasedAGI
Menu
Rankings live

developer_tools

Codebase onboarding brief

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

#1 Recommendation

gemini-3-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)

external/google/gemini-3-pro-preview

27.7%

Score

35.2%

Confidence

Limited benchmark evidence for this use case.

48 ranked models with average evidence of 15.3 points. Rankings may shift as more benchmark data is ingested.

Ranked Models

30

Evidence Quality

83%

Scoring

Benchmark-backed

Top Signal

FACTS Benchmark Suite: facts_grounding_score_pct

All Ranked Models

Max params:
Min confidence:
30 of 30
RankModelScore
#1gemini-3-pro-preview

Strong on FACTS Benchmark Suite facts_grounding_score_pct (88%) and FACTS Benchmark Suite facts_search_score_pct (100%)

27.7%
#2anthropic/claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct (100%) and Vals SWE-bench overall_accuracy_pct (95%)

22.1%
#3gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct (100%) and Vectara HHEM Leaderboard overall_hallucination_error_pct (76%)

21.9%
#4Grok-4-0709
21.0%
#5google/gemini-3.1-pro-preview
20.9%
#6gpt-4.1-20250414
20.9%
#7gpt-5-2025-08-07
20.8%
#8openai/gpt-5.4-2026-03-05
20.5%
#9claude-opus-4-5-20251101
19.7%
#10gpt-5-mini-2025-08-07
19.1%
#11gemini-3-flash-preview
18.2%
#12gpt-5.1-2025-11-13
18.1%
#13claude-sonnet-4-20250514
17.9%
#14anthropic/claude-opus-4-6-thinking
17.1%
#15gpt-5.2-2025-12-11
16.8%
#16google/gemini-3.1-flash-lite-preview
16.3%
#17xai-org/grok-4-fast-reasoning
16.0%
#18anthropic/claude-opus-4-5-20251101-thinking
15.9%
#19kimi/kimi-k2.5-thinking
15.6%
#20xai-org/grok-4-1-fast-reasoning
15.3%
#21z-ai/glm-4.7
14.8%
#23Kimi K2 Thinking
14.6%
#24zai/glm-5-thinking
14.6%
#25anthropic/claude-sonnet-4-5-20250929-thinking
14.5%
#26minimax/minimax-m2.1
14.3%
#29gpt-4o-2024-05-13
13.6%
#30alibaba/qwen3.5-flash
12.8%
#31gemini-2.5-flash
12.7%
#32anthropic/claude-haiku-4-5-20251001-thinking
12.4%
#34o3-20250416
12.1%

Compare Models

Model A leads by +5.5%

Shareable Link →

Model A

gemini-3-pro-preview

external/google/gemini-3-pro-preview

27.7%

Rank #1

Confidence 35.2%23 evidence pts

FACTS Benchmark Suite: facts_grounding_score_pct

Value 88.3% · Conf 100.0% · Weight 1.6%

facts_benchmark_suite.facts_grounding_score_pct (Mar 12, 2026)

FACTS Benchmark Suite: facts_search_score_pct

Value 100.0% · Conf 100.0% · Weight 1.4%

facts_benchmark_suite.facts_search_score_pct (Mar 12, 2026)

FACTS Benchmark Suite: average_score_pct

Value 100.0% · Conf 100.0% · Weight 1.3%

facts_benchmark_suite.average_score_pct (Mar 12, 2026)

Vals SWE-bench: overall_accuracy_pct

Value 87.5% · Conf 100.0% · Weight 1.3%

vals_swebench.overall_accuracy_pct (Mar 12, 2026)

Model B

anthropic/claude-sonnet-4.6

external/anthropic/claude-sonnet-4-6

22.1%

Rank #2

Confidence 27.3%17 evidence pts

Vals Finance Agent: overall_accuracy_pct

Value 100.0% · Conf 100.0% · Weight 1.5%

vals_finance_agent.overall_accuracy_pct (Mar 12, 2026)

Vals SWE-bench: overall_accuracy_pct

Value 95.1% · Conf 100.0% · Weight 1.4%

vals_swebench.overall_accuracy_pct (Mar 12, 2026)

Vals CorpFin v2: overall_accuracy_pct

Value 91.5% · Conf 100.0% · Weight 1.3%

vals_corp_fin_v2.overall_accuracy_pct (Mar 12, 2026)

Vals LiveCodeBench: overall_accuracy_pct

Value 91.2% · Conf 100.0% · Weight 1.2%

vals_lcb.overall_accuracy_pct (Mar 12, 2026)

Ranking Diagnostics & Missing Models

Source Lift

Ranked

48

Sources

8

Quality

Insufficient

Vals CorpFin v2

vals_corp_fin_v2

41 rows

0.9% avg lift

Vals LiveCodeBench

vals_lcb

40 rows

1.0% avg lift

Vals SWE-bench

vals_swebench

33 rows

1.0% avg lift

Vals MedQA

vals_medqa

33 rows

0.2% avg lift

Missing Strong Models

google/gemini-2.0-flash-001

external/google/gemini-2-0-flash-001

Rank #56

10.3%

Thin evidence after weighting

deepseek-v3

external/deepseek-ai/deepseek-v3

Rank #66

8.8%

Thin evidence after weighting
Taxonomy Details

Core Tasks

task.multi_doc_synthesistask.code_explanation

Required Modes

mode.long_context

Domains

domain.software_engineering

Related Use Cases