developer_tools
Function Calling / Tool Use Agent
Reliably selecting and invoking the correct tools/APIs in multi-step agentic pipelines.
#1 Recommendation
anthropic/claude-sonnet-4.6
Strong on OpenHands Issue Resolution issue_resolution_score_pct (72%) and Vals SWE-bench overall_accuracy_pct (95%)
external/anthropic/claude-sonnet-4-6
16.5%
Score
29.6%
Confidence
Limited benchmark evidence for this use case.
25 ranked models with average evidence of 17.4 points. Rankings may shift as more benchmark data is ingested.
Ranked Models
25
Evidence Quality
80%
Scoring
Benchmark-backed
Top Signal
OpenHands Issue Resolution: issue_resolution_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| #5 | anthropic/claude-sonnet-4.6 | 16.5% |
| #8 | kimi/kimi-k2.5-thinking | 14.8% |
| #11 | GLM-5 | 13.8% |
| #12 | gpt-4o | 13.4% |
| #13 | gemini-3-pro-preview | 12.8% |
| #15 | Kimi K2 Thinking | 12.6% |
| #16 | gpt-4.1-20250414 | 12.0% |
| #18 | gemini-2.5-pro | 11.1% |
| #19 | Grok-4-0709 | 11.0% |
| #21 | claude-sonnet-4-20250514 | 11.0% |
| #22 | minimax/minimax-m2.1 | 10.9% |
| #23 | qwen-2.5-72b-instruct | 10.6% |
| #24 | claude-opus-4-5-20251101 | 10.2% |
| #25 | gpt-5.2-2025-12-11 | 9.8% |
| #26 | gpt-4.1-mini-20250414 | 8.8% |
| #29 | gpt-4o-2024-08-06 | 8.7% |
| #30 | z-ai/glm-4.7 | 8.2% |
| #31 | gpt-5-2025-08-07 | 8.2% |
| #33 | deepseek/deepseek-r1 | 7.8% |
| #34 | gpt-4o-20241120 | 7.6% |
| #35 | o3-20250416 | 7.5% |
| #36 | gpt-4o-2024-05-13 | 6.9% |
| #37 | GLM-4.7 | 6.8% |
| #41 | GPT-4.1-nano-2025-04-14 | 4.0% |
| #42 | openai/gpt-4o-mini-2024-07-18 | 3.8% |
Compare Models
Model A leads by +1.7%
Shareable Link →Model A
anthropic/claude-sonnet-4.6
external/anthropic/claude-sonnet-4-6
Rank #5
OpenHands Issue Resolution: issue_resolution_score_pct
Value 71.8% · Conf 100.0% · Weight 2.3%
openhands_issue_resolution.issue_resolution_score_pct (Mar 17, 2026)
Vals SWE-bench: overall_accuracy_pct
Value 95.1% · Conf 100.0% · Weight 1.4%
vals_swebench.overall_accuracy_pct (Mar 17, 2026)
Vals LiveCodeBench: overall_accuracy_pct
Value 91.2% · Conf 100.0% · Weight 1.2%
vals_lcb.overall_accuracy_pct (Mar 17, 2026)
Vals Terminal-Bench 2: overall_accuracy_pct
Value 87.9% · Conf 100.0% · Weight 1.1%
vals_terminal_bench_2.overall_accuracy_pct (Mar 17, 2026)
Model B
kimi/kimi-k2.5-thinking
external/kimi/kimi-k2-5-thinking
Rank #8
Vals LiveCodeBench: overall_accuracy_pct
Value 93.6% · Conf 100.0% · Weight 1.2%
vals_lcb.overall_accuracy_pct (Mar 17, 2026)
Vals SWE-bench: overall_accuracy_pct
Value 82.6% · Conf 100.0% · Weight 1.2%
vals_swebench.overall_accuracy_pct (Mar 17, 2026)
OpenHands Index: information_gathering_score_pct
Value 75.4% · Conf 100.0% · Weight 1.0%
openhands_index.information_gathering_score_pct (Mar 17, 2026)
OpenHands Index: average_score_pct
Value 35.5% · Conf 100.0% · Weight 0.9%
openhands_index.average_score_pct (Mar 17, 2026)
▶Ranking Diagnostics & Missing Models
Source Lift
Ranked
25
Sources
8
Quality
Insufficient
Vals LiveCodeBench
vals_lcb
17 rows
0.9% avg lift
Vals SWE-bench
vals_swebench
15 rows
1.0% avg lift
Vals MedQA
vals_medqa
15 rows
0.2% avg lift
Vals Legal Bench
vals_legal_bench
14 rows
0.2% avg lift
Missing Strong Models
gpt-5-mini-2025-08-07
external/openai/gpt-5-mini-2025-08-07
Rank #7
19.1%
google/gemini-3.1-pro-preview
external/google/gemini-3-1-pro-preview
Rank #8
18.6%
openai/gpt-5.4-2026-03-05
external/openai/gpt-5-4-2026-03-05
Rank #9
18.3%
gemini-2.5-flash
external/google/gemini-2-5-flash
Rank #10
17.6%
▶Taxonomy Details
Core Tasks
Required Modes
Domains
Related Use Cases
developer_tools
Codebase onboarding brief
Summarize a repository's architecture, modules, and conventions.
Top: gemini-3-pro-preview
developer_tools
Code generation
Generate correct, secure code from requirements.
Top: GLM-5
developer_tools
Autonomous Coding Agent
End-to-end autonomous software engineering: reading issues, writing code, running tests, submitting PRs.
Top: Kimi K2 Thinking
developer_tools
Refactoring assistant
Refactor code safely while preserving behavior and improving clarity.
Top: Kimi K2 Thinking