Consensus score
82.4
95% interval 75.5 to 86.8
82.4
95% interval 75.5 to 86.8
68th
IQR spread 26.7 pct
36
Across 6 domains
4
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 | #6 / 38Tied #1 | 44.4%[37.3% to 51.4%] | $0.46 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Vibe Code Bench Vals AI benchmarks · max · OpenHands | #10 / 38 | 87.7%[82.3% to 93.1%] | $0.58 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Code Migration Vals AI benchmarks · max | #11 / 38 | 68.5%[61.7% to 75.3%] | $1.57 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev HTML · max | #11 / 155 | 1,694[1,680 to 1,708] | Unknown | Standard | 15 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · max · DeepSeek Harness | #13 / 145 | 42.7 | $1.84 | On frontier. Evidence grade A of A to D: strongest. | 18 Oct 2026 |
| LMArena WebDev LMArena · Image to webdev · max | #13 / 64 | 1,609[1,599 to 1,619] | Unknown | Standard | 15 Nov 2026 |
| Legal Agent Benchmark (HLAB-Vals) Vals AI benchmarks · max | #13 / 38 | 14.2%[8.7% to 19.6%] | $0.61 | Standard | 15 Nov 2026 |
| Vals Index Vals AI benchmarks · max | #13 / 38 | 61.3%[59.2% to 63.3%] | $0.66 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · max · Pi | #15 / 145 | 42.2 | $0.83 | On frontier. Evidence grade A of A to D: strongest. | 18 Oct 2026 |
| Legal Research Vals AI benchmarks · max | #16 / 38 | 45.2%[38.4% to 52%] | $0.70 | Standard | 15 Nov 2026 |
| Finance Agent Vals AI benchmarks · max | #18 / 38 | 62.9%[59% to 66.9%] | $0.47 | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Overall · max | #18 / 156 | 1,661[1,655 to 1,668] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev · max | #18 / 156 | 1,661[1,655 to 1,668] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev react · max | #18 / 140 | 1,673[1,666 to 1,681] | Unknown | Standard | 15 Nov 2026 |
| Terminal-Bench 4 Vals AI benchmarks · max | #20 / 38 | 31.8%[26.7% to 37%] | $0.54 | Standard | 15 Nov 2026 |
| EMB Vals AI benchmarks · max | #22 / 38 | 69.2%[64.5% to 73.9%] | $0.33 | Standard | 15 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · high · Pi | #23 / 145 | 40.4 | $0.64 | On frontier. Evidence grade A of A to D: strongest. | 18 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · high · DeepSeek Harness | #25 / 145 | 39.2 | $1.27 | Standard | 18 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · max · Claude Code | #26 / 145 | 39.1 | $1.01 | Standard | 18 Oct 2026 |
| CursorBench CursorBench · max · Cursor | #27 / 91 | 47.7% | $0.98 | On frontier. Evidence grade A of A to D: strongest. | Not stated |
| GPQA diamond Epoch AI Benchmarking Hub · max | #27 / 338Tied #1 | 93.2%[90.1% to 96.3%] | Unknown | Standard | 19 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · max · OpenCode | #28 / 145 | 37.6 | $0.96 | Standard | 18 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · high · OpenCode | #29 / 145 | 36.6 | $0.79 | Standard | 19 Oct 2026 |
| LMArena Agent LMArena · Overall · max | #29 / 64 | 0[0 to 0] | $0.14 | Standard | 15 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · high · Claude Code | #31 / 145 | 36.4 | $0.82 | Standard | 17 Oct 2026 |
| CursorBench CursorBench · medium · Cursor | #31 / 91 | 46.3% | $0.80 | On frontier. Evidence grade A of A to D: strongest. | Not stated |
| CursorBench CursorBench · high · Cursor | #35 / 91 | 45.6% | $0.77 | On frontier. Evidence grade A of A to D: strongest. | Not stated |
| Bug Hunt Bench Bug Hunt Bench · low · DeepSeek Harness | #37 / 145 | 34.8 | $1.06 | Standard | 18 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · low · Claude Code | #38 / 145 | 34.4 | $0.71 | Standard | 17 Oct 2026 |
| CursorBench CursorBench · low · Cursor | #38 / 91 | 44.9% | $0.60 | On frontier. Evidence grade A of A to D: strongest. | Not stated |
| Bug Hunt Bench Bug Hunt Bench · low · Pi | #42 / 145 | 33.8 | $0.46 | On frontier. Evidence grade A of A to D: strongest. | 18 Oct 2026 |
| Bug Hunt Bench Bug Hunt Bench · low · OpenCode | #44 / 145 | 32.8 | $0.66 | Standard | 19 Oct 2026 |
| ARC-AGI-2 Epoch AI Benchmarking Hub · max | #55 / 299 | 78.1% | Unknown | Standard | Not stated |
| ARC-AGI-2 Epoch AI Benchmarking Hub · low | #68 / 299 | 73.6% | Unknown | Standard | Not stated |
| ARC-AGI-2 Epoch AI Benchmarking Hub · high | #78 / 299 | 68.6% | Unknown | Standard | Not stated |
| ARC-AGI-2 Epoch AI Benchmarking Hub · none | #235 / 299 | 2.1% | Unknown | Standard | Not stated |
Same benchmark and harness measured across multiple reasoning effort settings.
Epoch AI Benchmarking Hub
2.1
73.6
68.6
78.1
Bug Hunt Bench · Claude Code
34.4
$0.71
36.4
$0.82
39.1
$1.01
Bug Hunt Bench · DeepSeek Harness
34.8
$1.06
39.2
$1.27
42.7
$1.84
Bug Hunt Bench · OpenCode
32.8
$0.66
36.6
$0.79
37.6
$0.96
Bug Hunt Bench · Pi
33.8
$0.46
40.4
$0.64
42.2
$0.83
CursorBench · Cursor
44.9
$0.60
46.3
$0.80
45.6
$0.77
47.7
$0.98
Direct pairwise win rates for DeepSeek V4.1 Flash 1017 across shared benchmark boards.
15 shared boards
13% win
Head-to-head15 shared boards
90% win
Head-to-head15 shared boards
7% win
Head-to-head15 shared boards
0% win
Head-to-head15 shared boards
73% win
Head-to-head15 shared boards
73% win
Head-to-head15 shared boards
13% win
Head-to-head15 shared boards
13% win
Head-to-head14 shared boards
71% win
Head-to-head14 shared boards
29% win
Head-to-head