Consensus score
64.7
95% interval 54.9 to 69.8
64.7
95% interval 54.9 to 69.8
30th
IQR spread 12.2 pct
14
Across 4 domains
2
Newest observation 2d ago
Median within-board percentile by capability domain across boards with sufficient peer overlap.
Best verified run per board, with confidence intervals and Pareto frontier status.
| Benchmark | Rank | Score | Cost | Status | Observed |
|---|---|---|---|---|---|
| Tax Agent Vals AI benchmarks · max | #19 / 38 | 32.1%[25.6% to 38.7%] | $0.32 | Standard | 15 Nov 2026 |
| Code Migration Vals AI benchmarks · max | #23 / 38 | 48.2%[41.6% to 54.8%] | $1.73 | Standard | 15 Nov 2026 |
| Terminal-Bench 4 Vals AI benchmarks · max | #25 / 38 | 25.3%[23.3% to 27.2%] | $0.73 | Standard | 15 Nov 2026 |
| EMB Vals AI benchmarks · max | #27 / 38 | 67.8%[63.4% to 72.3%] | $0.27 | Standard | 15 Nov 2026 |
| Legal Agent Benchmark (HLAB-Vals) Vals AI benchmarks · max | #27 / 38 | 7.5%[3.1% to 11.9%] | $0.47 | Standard | 15 Nov 2026 |
| Vals Index Vals AI benchmarks · max | #27 / 38 | 53.8%[51.7% to 55.9%] | $0.66 | Standard | 15 Nov 2026 |
| Finance Agent Vals AI benchmarks · max | #30 / 38 | 58.8%[54.8% to 62.9%] | $0.16 | Standard | 15 Nov 2026 |
| Legal Research Vals AI benchmarks · max | #31 / 38 | 34.1%[27.7% to 40.6%] | $0.44 | Standard | 15 Nov 2026 |
| Vibe Code Bench Vals AI benchmarks · max · OpenHands | #31 / 38 | 73.9%[65.6% to 82.3%] | $1.15 | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev react · Default | #40 / 140 | 1,601[1,589 to 1,612] | Unknown | Standard | 15 Nov 2026 |
| LMArena Agent LMArena · Overall · Default | #43 / 64 | -0[-0 to -0] | $0.21 | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Overall · Default | #43 / 156 | 1,582[1,573 to 1,591] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev · Default | #43 / 156 | 1,582[1,573 to 1,591] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev HTML · Default | #48 / 155 | 1,554[1,531 to 1,578] | Unknown | Standard | 15 Nov 2026 |
Direct pairwise win rates for MiniMax M3.1 Flash across shared benchmark boards.
11 shared boards
100% win
Head-to-head11 shared boards
0% win
Head-to-head11 shared boards
18% win
Head-to-head11 shared boards
0% win
Head-to-head11 shared boards
45% win
Head-to-head11 shared boards
18% win
Head-to-head11 shared boards
73% win
Head-to-head11 shared boards
18% win
Head-to-head11 shared boards
36% win
Head-to-head11 shared boards
27% win
Head-to-head