← Grok 4.5 · API · High effort
Evidenceacceptedthird_party_leaderboard
SWE-bench Verified
Vals.ai SWE-bench Verified (mini-swe-agent) — Grok 4.5
ev_2026_07_grok45_swe_vals
Result
86.6%
Confidence A
- Tested
- 2026-07-09
- Runs
- 1
Configuration
How it was measured
- Exact model
- grok-4.5
- Reasoning
- high
- Agent harness
- mini-swe-agent
- Tool access
- bash only
- Prompting
- Vals default; max tokens raised
PRIMARY STR — independent Vals mini-swe-agent board.
Caveats
Known limitations
- mini-swe-agent minimal harness; Grok Build / richer agents can differ.
- High reasoning config.
- Do not equate with vendor SWE-bench Pro 64.7%.
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance0.95
quality0.85
recency1.00
health0.80
comparability0.90
reliability0.85
Benchmark
SWE-bench Verified
Human-filtered 500-instance subset of SWE-bench evaluating whether models can resolve real GitHub issues in existing repositories under a controlled agent harness.
Benchmark source →