Skip to content

Benchmarks

Sources
8
Entries tracked
22,318
Last sync
35 min
All sources syncing normally
  • Arena · Text3 hours ago
  • Arena · WebDev3 hours ago
  • Arena · Vision3 hours ago
  • Arena · Agent3 hours ago
  • GPQA Diamond35 minutes ago
  • SWE-bench35 minutes ago
  • Terminal-Bench35 minutes ago
  • ARC-AGI-235 minutes ago

MiniMax-M2.7

45.1%

no interval published

MiniMaxApr 2026swing #67–#241

MiniMax-M2.5

42.7%±2.8%

39.9%CI45.5%

MiniMaxFeb 2026swing #82–#458

MiniMax-M2.1

36.6%±2.9%

33.7%CI39.5%

MiniMaxDec 2025swing #34–#201

Terminal-Bench ×14 of 44 models
ModelOrg± CISwingAdd to compare
20MiniMax-M2.7MiniMaxApr 2026$0.30 / $1.2045.1%—#67–241
23MiniMax-M2.5MiniMaxFeb 2026$0.27 / $0.9542.7%39.9%–45.5%#82–458
26MiniMax-M2.1MiniMaxDec 2025$0.30 / $1.2036.6%33.7%–39.5%#34–201
32MiniMax-M2MiniMaxOct 2025$0.26 / $1.0230.0%27.3%–32.8%#135–415

Showing Terminal-Bench exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.