Unverified50% confidenceBenchmarkExact time
Officially published benchmark results: LiveCodeBench v6 score of 88.57 versus 89.71 for the base model, retaining 98.7%; SWE-bench Verified score of 77.00 versus 81.20 for the base model, retaining 94.8%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedJetBrains self-reported evaluation results: Mellum2.1 scores 47.0% on SWE-bench Verified, 28.0% on SWE-bench Pro, 17.4% on Terminal-Bench 2.1, 82.0% on LiveCodeBench v6, and 91.5% on HumanEval+.70% similarUnverifiedIn seven LiveBench evaluations, Terra scored 77.8 overall, with 48.6 on the agency item, far below its coding (94.3) and browsing (93.1) scores.69% similarUnverifiedThe IQ3S tier scores 92.93 on GPQA Diamond (vs. BF16 baseline 91.92), 86.86 on LiveCodeBench V6 (vs. 87.43), with a three-task average of 93.26 vs. 93.12, and a file size less than one quarter of BF16 (approximately 22%).67% similarUnverifiedPruning-based weakening raises the accuracy of Qwen3.5-4B on LiveCodeBench v6 from 39.1% to 56.7%.67% similarUnverifiedBenchmarked against Qwen3.8-27B, Agens Volundr 32B leads on LiveCodeBench v6 (+4.2), HumanEval (+4.3), AIME 2025 (+2.9), and MATH-500 (+1.6).66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1127283API
curl https://kongchang.com/api/v1/knowledge/claims/1127283MCP
get_claim(id=1127283)