Unverified50% confidenceBenchmarkExact time
On agent tasks, Agens Volundr 32B lags behind: tau2-bench scores 74.2 (competitor 79–80), and SWE-bench Verified (50-question subset) is only 44 (competitor 58–64).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4.1 claims to achieve 74 on SWE, but the blogger found that this was the best result cherry-picked from multiple tests, with open code testing at 65 and PI testing at 66.63% similarUnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.62% similarUnverifiedIn Path A, an RTX 3060 runs the front layers and an AMD AI Max+ 395 runs the back layers, improving Prefill speed from 136.69 token/s to 319.1 token/s under IQ3 quantization with 64K long input.61% similarUnverifiedThe Luna model's fail_fast/endstate score is 64/55, with the gap corresponding to trajectories that appear clean turn by turn but end in a corrupted final state.61% similarUnverifiedMiniCPM5-2B's score on SWE-bench beats 4B-class competitors with twice its parameter count.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977118API
curl https://kongchang.com/api/v1/knowledge/claims/977118MCP
get_claim(id=977118)