Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Qwen3.5 397B has the cleaner overall profile here, landing at 60 versus 57. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
MiniMax M2.7 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5 397B. That is roughly Infinityx on output cost alone. MiniMax M2.7 gives you the larger context window at 200K, compared with 128K for Qwen3.5 397B.
Pick Qwen3.5 397B if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if coding is the priority or you need the larger 200K context window.
MiniMax M2.7
57
Qwen3.5 397B
56.9
MiniMax M2.7
56.2
Qwen3.5 397B
40.7
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Qwen3.5 397B is ahead overall, 60 to 57. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 56.2% and 42%.
MiniMax M2.7 has the edge for coding in this comparison, averaging 56.2 versus 40.7. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 versus 56.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.