Consensus score
95.3
95% interval 83.7 to 100.0
95.3
95% interval 83.7 to 100.0
99th
IQR spread 4.0 pct
31
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 |
|---|---|---|---|---|---|
| Bug Hunt Bench Bug Hunt Bench · max · Claude Code | #1 / 145Tied #1 | 58 | $139.65 | On frontier. Evidence grade A of A to D: strongest. | 9 Nov 2026 |
| EMB Vals AI benchmarks · high | #1 / 38Tied #1 | 77.4%[73.1% to 81.7%] | $6.67 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Finance Agent Vals AI benchmarks · high | #1 / 38Tied #1 | 69.5%[65.6% to 73.3%] | $4.83 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| LMArena Agent LMArena · Overall · max | #1 / 64Tied #1 | 0.3[0.2 to 0.3] | $9.02 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| LMArena WebDev LMArena · Overall · xhigh | #1 / 156Tied #1 | 1,826[1,807 to 1,845] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev · xhigh | #1 / 156Tied #1 | 1,826[1,807 to 1,845] | Unknown | Standard | 15 Nov 2026 |
| LMArena WebDev LMArena · Webdev react · xhigh | #1 / 140Tied #1 | 1,895[1,869 to 1,921] | Unknown | Standard | 15 Nov 2026 |
| Terminal-Bench 4 Vals AI benchmarks · high | #1 / 38Tied #1 | 65.2%[60.6% to 69.7%] | $14.56 | Standard | 15 Nov 2026 |
| Vals Index Vals AI benchmarks · high | #1 / 38Tied #1 | 71.3%[69.4% to 73.2%] | $17.94 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Vibe Code Bench Vals AI benchmarks · high · OpenHands | #1 / 38Tied #1 | 93.8%[91.5% to 96%] | $22.13 | On frontier. Evidence grade A of A to D: strongest. | 15 Nov 2026 |
| Code Migration Vals AI benchmarks · high | #2 / 38Tied #1 | 85.8%[78.9% to 92.8%] | $68.68 | Standard | 15 Nov 2026 |
| CursorBench CursorBench · max · Cursor | #3 / 91 | 60% | $32.79 | Standard | Not stated |
| GPQA diamond Epoch AI Benchmarking Hub · max · fallback | #3 / 338Tied #1 | 96%[93.4% to 98.6%] | Unknown | Standard | 6 Nov 2026 |
| ARC-AGI-2 Epoch AI Benchmarking Hub · xhigh | #4 / 299 | 93.8% | Unknown | Standard | Not stated |
| LMArena WebDev LMArena · Webdev HTML · xhigh | #4 / 155Tied #1 | 1,760[1,717 to 1,804] | Unknown | Standard | 15 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · xhigh · Claude Code | #5 / 145 | 49 | $61.01 | Standard | 10 Nov 2026 |
| ARC-AGI-2 Epoch AI Benchmarking Hub · max | #7 / 299 | 92.5% | Unknown | Standard | Not stated |
| CursorBench CursorBench · high · Cursor | #7 / 91 | 56.9% | $9.70 | Standard | Not stated |
| CursorBench CursorBench · xhigh · Cursor | #8 / 91 | 56.3% | $15.48 | Standard | Not stated |
| Bug Hunt Bench Bug Hunt Bench · high · Claude Code | #10 / 145 | 43 | $46.67 | Standard | 10 Nov 2026 |
| CursorBench CursorBench · medium · Cursor | #12 / 91 | 54.8% | $4.66 | Standard | Not stated |
| Legal Research Vals AI benchmarks · high | #13 / 38 | 46.2%[39.4% to 52.9%] | $3.96 | Standard | 15 Nov 2026 |
| CursorBench CursorBench · low · Cursor | #14 / 91 | 53.2% | $3.94 | On frontier. Evidence grade A of A to D: strongest. | Not stated |
| ARC-AGI-2 Epoch AI Benchmarking Hub · high | #18 / 299 | 90.4% | Unknown | Standard | Not stated |
| Bug Hunt Bench Bug Hunt Bench · medium · Claude Code | #18 / 145 | 41.5 | $26.55 | Standard | 10 Nov 2026 |
| Bug Hunt Bench Bug Hunt Bench · low · Claude Code | #20 / 145 | 41 | $24.32 | Standard | 10 Nov 2026 |
| GPQA diamond Epoch AI Benchmarking Hub · max | #20 / 338Tied #1 | 93.9%[90.7% to 97.1%] | Unknown | Standard | 6 Nov 2026 |
| Tax Agent Vals AI benchmarks · high | #21 / 38 | 32.1%[25.5% to 38.7%] | $3.31 | Standard | 15 Nov 2026 |
| ARC-AGI-2 Epoch AI Benchmarking Hub · medium | #23 / 299 | 89.6% | Unknown | Standard | Not stated |
| Legal Agent Benchmark (HLAB-Vals) Vals AI benchmarks · high | #30 / 38 | 5%[1.6% to 8.4%] | $19.37 | Standard | 15 Nov 2026 |
| ARC-AGI-2 Epoch AI Benchmarking Hub · low | #34 / 299 | 86.7% | Unknown | Standard | Not stated |
Same benchmark and harness measured across multiple reasoning effort settings.
Epoch AI Benchmarking Hub
86.7
89.6
90.4
93.8
92.5
Bug Hunt Bench · Claude Code
41.0
$24.32
41.5
$26.55
43.0
$46.67
49.0
$61.01
58.0
$139.65
CursorBench · Cursor
53.2
$3.94
54.8
$4.66
56.9
$9.70
56.3
$15.48
60.0
$32.79
Direct pairwise win rates for Fable 5.2 across shared benchmark boards.
15 shared boards
87% win
Head-to-head15 shared boards
93% win
Head-to-head15 shared boards
73% win
Head-to-head15 shared boards
60% win
Head-to-head15 shared boards
80% win
Head-to-head15 shared boards
100% win
Head-to-head15 shared boards
77% win
Head-to-head15 shared boards
73% win
Head-to-head14 shared boards
79% win
Head-to-head14 shared boards
86% win
Head-to-head