RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Fable 5.1

130 benchmarks · 307 observations · 109 sources · released 2026-09-01

Scores at a glance

122 benchmarks · large dot: Claude Fable 5.1; small dots: closest models where reported

AA-Briefcase v1.1 ↗1669.43 Elo
833.061811.82

Claude Fable 5.1 (Max, Default Fallback) · AA-Briefcase v1.1 · overall Elo ↗

1 more reported result

1672 Elo · Claude Fable 5.1 (max, with fallback) · AA-Briefcase v1.1 · AA-Briefcase v1.1 (Elo-score) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

GDP.pdf ↗26.20%
7.432.6

Claude Fable 5.1 (Max, Default Fallback) · GDP.pdf · all-pass ↗

5 more reported results

27.6 · Claude Fable 5.1 (max) · GDP.pdf · Muse Wonder official evaluation report ↗

29.6% · Claude Fable 5.1 (high) · GDP.pdf · GDP.pdf score · % · Epoch AI · GDP.pdf ↗

27.6% · Claude Fable 5.1 (max) · GDP.pdf · GDP.pdf score · % · Epoch AI · GDP.pdf ↗

83.8% · Claude Fable 5.1 (max, with fallback) · GDP.pdf · GDP.pdf w/ python · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

27.6% · Claude Fable 5.1 (max, with fallback) · GDP.pdf · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

Terminal-Bench 4.0 ↗52.02%
067.17

Claude Fable 5.1 (Max, Default Fallback) · Terminal-Bench 4.0 · AA harness ↗

6 more reported results

58.08 % · Claude Fable 5.1 (Mini-SWE-agent) · Terminal-Bench 4.0 · Score · Vals AI · Terminal-Bench 4.0 ↗

57.9% · Claude Fable 5.1 · Terminal-Bench 4.0 · Gemini 4 Argon model card ↗

55.8% · Claude Fable 5.1 · Terminal-Bench 4.0 · GPT-6 Astra launch report ↗

55.8% · Fable 5.1 · Terminal-Bench 4.0 · Claude Opus 5.5 launch report ↗

52.0 · Claude Fable 5.1 (max) · Terminal-Bench 4.0-AA · Muse Wonder official evaluation report ↗

57.9% · Claude Fable 5.1 (max, with fallback) · Terminal-Bench 4.0 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

Terminal-Bench-Science 0.1 ↗43.33%
063.33

Claude Fable 5.1 (Max, Default Fallback) · Terminal-Bench-Science 0.1 · AA harness ↗

5 more reported results

40 % · Claude Fable 5.1 (Mini-SWE-agent) · Terminal-Bench-Science · Score · Vals AI · Terminal-Bench-Science ↗

52.6% · Claude Fable 5.1 · Terminal-Bench Science 0.1 · Gemini 4 Argon model card ↗

52.6% · Claude Fable 5.1 · Terminal-Bench Science 0.1 · GPT-6 Astra launch report ↗

52.6% · Fable 5.1 · Terminal-Bench-Science 0.1 · Claude Opus 5.5 launch report ↗

40% · Claude Fable 5.1 (max, with fallback) · Terminal-Bench-Science 0.1 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

FrontierCode 2.0 ↗31.62%
3.9246.44

Claude Fable 5.1 (Max, Default Fallback) · FrontierCode 2.0 · AA implementation ↗

AA-Omniscience v1.1 ↗46.27 index
-8.2748.13

Claude Fable 5.1 (Max, Default Fallback) · AA-Omniscience v1.1 · error-penalized index ↗

1 more reported result

43.45 index · Claude Fable 5.1 (Max, Default Fallback) · AA-Omniscience · error-penalized score · Artificial Analysis ↗

AA-3D ↗1134.76 Elo
572.551198.83

Claude Fable 5.1 (Max, Default Fallback) · AA-3D · Elo ↗

AA-AnalystAgent ↗57.50%
23.7560

Claude Fable 5.1 (Max, Default Fallback) · AA-AnalystAgent · strict score ↗

SciCode ↗63.08%
42.9466.9

Claude Fable 5.1 (Max, Default Fallback) · SciCode · AA implementation ↗

5 more reported results

63.08% · Claude Fable 5.1 (max) · SciCode · Score · % · Epoch AI · SciCode ↗

60.88% · Claude Fable 5.1 (xhigh) · SciCode · Score · % · Epoch AI · SciCode ↗

57.64% · Claude Fable 5.1 (high) · SciCode · Score · % · Epoch AI · SciCode ↗

55.67% · Claude Fable 5.1 (low) · SciCode · Score · % · Epoch AI · SciCode ↗

55.32% · Claude Fable 5.1 (medium) · SciCode · Score · % · Epoch AI · SciCode ↗

Humanity’s Last Exam ↗59.13%
30.7261.35

Claude Fable 5.1 (Max, Default Fallback) · Humanity’s Last Exam · AA implementation ↗

5 more reported results

65.0% · Claude Fable 5.1 · Humanity’s Last Exam · tools · GPT-6 Astra launch report ↗

65.6% · tools · Fable 5.1 · Humanity’s Last Exam · tools · Claude Opus 5.5 launch report ↗

46.5% · Claude Fable 5.1 (xhigh) · HLE · Accuracy · % · Epoch AI · HLE ↗

65.6% · Claude Fable 5.1 (max, with fallback) · Humanity’s Last Exam · HLE-Full w/ tools · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

57.6% · Claude Fable 5.1 (max, with fallback) · Humanity’s Last Exam · HLE-Full · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

ITBench-AA ↗49.53%
35.2256.21

Claude Fable 5.1 (Max, Default Fallback) · ITBench-AA · root-cause score ↗

MLCR-AA ↗15.56%
6.1141.67

Claude Fable 5.1 (Max, Default Fallback) · MLCR-AA · overall ↗

CritPt v2 ↗72.00%
483.14

Claude Fable 5.1 (Max, Default Fallback) · CritPt v2 · code tools ↗

CritPt ↗29.71%
4.5732.86

Claude Fable 5.1 (Max, Default Fallback) · CritPt · original ↗

5 more reported results

31.14% · Claude Fable 5.1 (xhigh) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

30.29% · Claude Fable 5.1 (high) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

29.71% · Claude Fable 5.1 (max) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

29.14% · Claude Fable 5.1 (medium) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

27.71% · Claude Fable 5.1 (low) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

AA-PersonalityBench ↗100.00 percentile
28.92100

Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · expressiveness ↗

7 more reported results

54.31 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · organization · Artificial Analysis ↗

97.46 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · informativeness · Artificial Analysis ↗

97.46 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · transparency · Artificial Analysis ↗

97.46 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · warmth · Artificial Analysis ↗

100.00 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · conviction · Artificial Analysis ↗

79.69 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · imagination · Artificial Analysis ↗

21.31 percentile · Claude Fable 5.1 (Max, Default Fallback) · AA-PersonalityBench · slop · Artificial Analysis ↗

CursorBench 4.0 ↗51.8%
41.757.8

Fable 5.1 · CursorBench 4.0 ↗

5 more reported results

51.8% · Claude Fable 5.1 (max) · CursorBench · Score · % · Epoch AI · CursorBench ↗

51.6% · Claude Fable 5.1 (xhigh) · CursorBench · Score · % · Epoch AI · CursorBench ↗

49.2% · Claude Fable 5.1 (high) · CursorBench · Score · % · Epoch AI · CursorBench ↗

46.8% · Claude Fable 5.1 (medium) · CursorBench · Score · % · Epoch AI · CursorBench ↗

45.1% · Claude Fable 5.1 (low) · CursorBench · Score · % · Epoch AI · CursorBench ↗

PostTrainBench ↗40.2%
40.249.3

Claude Fable 5.1 · PostTrainBench ↗

1 more reported result

44.6% · Claude Fable 5.1 (max, with fallback) · PostTrainBench · PostTrain Bench v1.2 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

BenchCAD ↗84.3%†
67.595.9

Claude Fable 5.1 · BenchCAD · tools ↗

2 more reported results

60.6% · Claude Fable 5.1 (max, with fallback) · BenchCAD · BenchCAD w/o tools · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

92.6% · Claude Fable 5.1 (max, with fallback) · BenchCAD · BenchCAD w/ tools · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

ARC-AGI-2 ↗90.0%
89.295

Claude Fable 5.1 · ARC-AGI-2 ↗

5 more reported results

90% · Claude Fable 5.1 (max) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

90% · Claude Fable 5.1 (xhigh) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

88.75% · Claude Fable 5.1 (high) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

86.25% · Claude Fable 5.1 (medium) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

78.33% · Claude Fable 5.1 (low) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

SWE-Marathon ↗45.6
42.557.5

Claude Fable 5.1 (max) · SWE-Marathon ↗

1 more reported result

45.6% · Claude Fable 5.1 (max, with fallback) · SWE-Marathon · SWE Marathon v1.1 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

ErdősBench ↗3.250 / 4
2.113.25

Fable 5.1 xhigh · ErdősBench · mean progress / 4 · API ↗

Chess Puzzles ↗48%
076

Claude Fable 5.1 (max) · Chess Puzzles · Best score (across scorers) · % ↗

MirrorCode ↗73.3%
8.8977.4

Claude Fable 5.1 (high) · MirrorCode · Best score (across scorers) · % ↗

WeirdML (v3) ↗43.53%
4.3854.05

Claude Fable 5.1 (xhigh) · WeirdML v3 · Max performance · % ↗

SpireClimb ↗2%
025.67

Claude Fable 5.1 (max) · SpireClimb · Best score (across scorers) · % ↗

Vals RSI Index ↗0.44 reference score
00.46

Claude Fable 5.1 (max) · Compression · reference-anchored score ↗

3 more reported results

0.49 reference score · Claude Fable 5.1 (max) · LM training · reference-anchored score · Vals RSI Index · LM training ↗

0.23 reference score · Claude Fable 5.1 (max) · Harness engineering · reference-anchored score · Vals RSI Index · Harness engineering ↗

0.28 reference score · Claude Fable 5.1 (max) · Post-training · reference-anchored score · Vals RSI Index · Post-training ↗

MedCode ↗53.51 %
19.7263.57

Claude Fable 5.1 · MedCode · Accuracy ↗

MMMU-Pro ↗90.64 %
22.7790.64

Claude Fable 5.1 · MMMU Pro · Accuracy ↗

2 more reported results

88.4% · Claude Fable 5.1 (max, with fallback) · MMMU-Pro · MMMU-Pro w/ python · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

86.3% · Claude Fable 5.1 (max, with fallback) · MMMU-Pro · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

Fortress ↗13.72%
5.7874.39

Fable-5.1 · Scale Labs · Risk elicitation score ↗

BoxBench ↗72%
7277

Claude Fable 5.1 · BoxBench · weighted rubric accuracy · OpenAI · ChatGPT financial services launch ↗

FocusBench ↗36.6%
36.654.2

Claude Fable 5.1 (max) · FocusBench · score · Meta · Muse Wonder launch · maximum effort ↗

Kimi Code Bench 3.0 ↗58.8%
45.566.5

Claude Fable 5.1 (max, with fallback) · Kimi Code Bench 3.0 · Kimi Code Bench 3.0 Long-horizon (Internal) · Kimi K3.1 Pro · complete release comparison ↗

BioMysteryBench ↗81.6%
78.981.9

Claude Fable 5.1 (max, with fallback) · BioMysteryBench · Kimi K3.1 Pro · complete release comparison ↗

CharXiv ↗92.7%
85.693.8

Claude Fable 5.1 (max, with fallback) · CharXiv · CharXiv (RQ) w/ python · Kimi K3.1 Pro · complete release comparison ↗

1 more reported result

88.8% · Claude Fable 5.1 (max, with fallback) · CharXiv · CharXiv (RQ) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

BabyVision ↗95.1%
92.597.7

Claude Fable 5.1 (max, with fallback) · BabyVision · BabyVision w/ python · Kimi K3.1 Pro · complete release comparison ↗

ZeroBench ↗59%
5163

Claude Fable 5.1 (max, with fallback) · ZeroBench · ZeroBench_main w/ python (pass@5) · Kimi K3.1 Pro · complete release comparison ↗

2 more reported results

23% · Claude Fable 5.1 (max, with fallback) · ZeroBench · ZeroBench_main · avg@5 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

35% · Claude Fable 5.1 (max, with fallback) · ZeroBench · ZeroBench_main · pass@5 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

OfficeQA Pro ↗54.5%
31.164.4

Claude Fable 5.1 (max, with fallback) · OfficeQA Pro · OfficeQA Pro v2 ↗

1 more reported result

68.6% · Claude Fable 5.1 (max, with fallback) · OfficeQA Pro · OfficeQA Pro v1 · Introducing Kimi K3.1 Pro ↗

HANDBOOK.md ↗38.8%
20.844.6

Claude Fable 5.1 (max, with fallback) · HANDBOOK.md · Kimi K3.1 Pro · complete release comparison ↗

Kimi Hallucination Benchmark ↗23.3%
5.523.3

Claude Fable 5.1 (max, with fallback) · Kimi Hallucination Benchmark · Kimi Hallu Bench Hard w/ tools (Internal, lower is better) · Kimi K3.1 Pro · complete release comparison ↗

1 more reported result

11.4% · Claude Fable 5.1 (max, with fallback) · Kimi Hallucination Benchmark · Kimi Hallu Bench w/o tools (Internal, lower is better) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗

ExploitBench ↗83%
54.4100

Claude Fable 5.1 (max, with fallback) · ExploitBench · Kimi K3.1 Pro · complete release comparison ↗

GDPx v1.0 ↗8.5%
1.6712.03

Claude Fable 5.1 · GDPx v1.0 · Overall · intended grading ↗

53 more reported results

8.6% · Claude Fable 5.1 · GDPx v1.0 · Eight-domain subset · intended grading · GDPx v1.0 — SemiAnalysis ↗

16.5% · Claude Fable 5.1 · GDPx v1.0 · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.8% · Claude Fable 5.1 · GDPx v1.0 · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Fable 5.1 · GDPx v1.0 · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

20.5% · Claude Fable 5.1 · GDPx v1.0 · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗

28.6% · Claude Fable 5.1 · GDPx v1.0 · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

8.3% · Claude Fable 5.1 · GDPx v1.0 · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

9.7% · Claude Fable 5.1 · GDPx v1.0 · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

1.2% · Claude Fable 5.1 · GDPx v1.0 · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

4.4% · Claude Fable 5.1 · GDPx v1.0 · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

16.4% · Claude Fable 5.1 · GDPx v1.0 · Overall · partial credit · GDPx v1.0 — SemiAnalysis ↗

18.2% · Claude Fable 5.1 · GDPx v1.0 · Eight-domain subset · partial credit · GDPx v1.0 — SemiAnalysis ↗

16.5% · Claude Fable 5.1 · GDPx v1.0 · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

5.4% · Claude Fable 5.1 · GDPx v1.0 · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.3% · Claude Fable 5.1 · GDPx v1.0 · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

27.4% · Claude Fable 5.1 · GDPx v1.0 · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

33.1% · Claude Fable 5.1 · GDPx v1.0 · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

29.2% · Claude Fable 5.1 · GDPx v1.0 · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

28.6% · Claude Fable 5.1 · GDPx v1.0 · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

8.3% · Claude Fable 5.1 · GDPx v1.0 · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

19.7% · Claude Fable 5.1 · GDPx v1.0 · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

1.2% · Claude Fable 5.1 · GDPx v1.0 · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

4.4% · Claude Fable 5.1 · GDPx v1.0 · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗

2.0% · Claude Fable 5.1 · GDPx v1.0 · Aria · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Arcverex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.5% · Claude Fable 5.1 · GDPx v1.0 · Ergodex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Fable 5.1 · GDPx v1.0 · Arithmetic · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

20.5% · Claude Fable 5.1 · GDPx v1.0 · LatchBio · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Living Context · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Chakra · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗

28.6% · Claude Fable 5.1 · GDPx v1.0 · Third Moment · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

16.5% · Claude Fable 5.1 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

8.3% · Claude Fable 5.1 · GDPx v1.0 · Beautiful Machines · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

7.4% · Claude Fable 5.1 · GDPx v1.0 · ValenceForge · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

12.0% · Claude Fable 5.1 · GDPx v1.0 · Emulated · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

1.2% · Claude Fable 5.1 · GDPx v1.0 · Fleet · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

4.4% · Claude Fable 5.1 · GDPx v1.0 · Datacurve · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

15.8% · Claude Fable 5.1 · GDPx v1.0 · Aria · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Fable 5.1 · GDPx v1.0 · Arcverex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

0.5% · Claude Fable 5.1 · GDPx v1.0 · Ergodex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.3% · Claude Fable 5.1 · GDPx v1.0 · Arithmetic · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

27.4% · Claude Fable 5.1 · GDPx v1.0 · LatchBio · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

33.1% · Claude Fable 5.1 · GDPx v1.0 · Living Context · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

29.2% · Claude Fable 5.1 · GDPx v1.0 · Chakra · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

28.6% · Claude Fable 5.1 · GDPx v1.0 · Third Moment · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

16.5% · Claude Fable 5.1 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

8.3% · Claude Fable 5.1 · GDPx v1.0 · Beautiful Machines · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

23.7% · Claude Fable 5.1 · GDPx v1.0 · ValenceForge · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

15.7% · Claude Fable 5.1 · GDPx v1.0 · Emulated · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

1.2% · Claude Fable 5.1 · GDPx v1.0 · Fleet · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

4.4% · Claude Fable 5.1 · GDPx v1.0 · Datacurve · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Reports featuring this model

Kimi K3.1 Pro · Kimi →

Claude Opus 5.5 · Anthropic →

GPT-6 Astra · OpenAI →

Muse Wonder and Muse Wonder Full · Meta →

Gemini 4 Argon · Google →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  2. Arena leaderboard — WebDev evaluation ↗

    Arena

  3. AA-3D: Interactive 3D Experience Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. AA-AnalystAgent Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. AA-PersonalityBench: AI Personality & Communication Style Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗

    Artificial Analysis

  8. AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗

    Artificial Analysis

  10. CritPt Benchmark | Artificial Analysis ↗

    Artificial Analysis

  11. CritPt v2 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  12. CritPt v2 — Hard Subset — Artificial Analysis ↗

    Artificial Analysis

  13. FrontierCode 1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  14. FrontierCode 2.0 Benchmark — Artificial Analysis ↗

    Artificial Analysis

  15. GDP.pdf Benchmark | Artificial Analysis ↗

    Artificial Analysis

  16. GDPval-AA v2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  17. GPQA Diamond Benchmark | Artificial Analysis ↗

    Artificial Analysis

  18. Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  19. HealthBench Professional Benchmark | Artificial Analysis ↗

    Artificial Analysis

  20. HLE-Diamond Benchmark — Artificial Analysis ↗

    Artificial Analysis

  21. Humanity's Last Exam Benchmark | Artificial Analysis ↗

    Artificial Analysis

  22. ITBench-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  23. MLCR-AA: Medical Long Context Reasoning Benchmark | Artificial Analysis ↗

    Artificial Analysis

  24. AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗

    Artificial Analysis

  25. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  26. 𝜏³-Banking Benchmark | Artificial Analysis ↗

    Artificial Analysis

  27. Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  28. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  29. Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  30. TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts — published result table ↗

    Jaffe, Oliver, Sherburn, Dane · 2026

  31. FrontierCode Leaderboard ↗

    Cognition

  32. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  33. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  34. Cursor · CursorBench ↗

    Cursor

  35. Gemini 4 Argon Model Card ↗

    Google DeepMind · 2026

  36. Muse Wonder | Meta ↗

    Meta AI

  37. APEX-Agents ↗

    Epoch AI

  38. ARC-AGI-2 ↗

    Epoch AI

  39. Chess Puzzles ↗

    Epoch AI

  40. CritPt v1 ↗

    Epoch AI

  41. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  42. FrontierMath Erdős ↗

    Epoch AI

  43. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  44. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  45. Furniture Assembly Benchmark ↗

    Epoch AI

  46. Humanity's Last Exam ↗

    Epoch AI

  47. MirrorCode ↗

    Epoch AI

  48. Mystery Game Puzzles ↗

    Epoch AI

  49. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  50. SimpleQA Verified ↗

    Epoch AI

  51. SpireClimb ↗

    Epoch AI

  52. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  53. AI benchmarks & capabilities ↗

    Epoch AI

  54. GDPx v1.0: The General Agentic Benchmark — SemiAnalysis ↗

    SemiAnalysis · 2026

  55. WeirdML ↗

    Håvard Tveit Ihle

  56. DistressBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  57. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  58. HiL-Bench (Human-in-Loop Benchmark) — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  59. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  60. Humanity's Sixth Sense — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  61. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  62. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  63. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  64. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  65. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  66. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  67. SWE Atlas - Refactoring — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  68. GPT-6 Astra: A new generation of intelligence ↗

    OpenAI

  69. Introducing ChatGPT for financial services ↗

    OpenAI · 2026

  70. Introducing Muse Wonder ↗

    Meta AI · 2026

  71. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  72. Introducing Claude Opus 5.5 ↗

    Anthropic

  73. FrontierSWE — software engineering benchmark ↗

    FrontierSWE

  74. Introducing Kimi K3.1 Pro ↗

    Moonshot AI · 2026

  75. ErdősBench: research mathematics, scoped progress and proof audits ↗

    Ulam AI · 2026

  76. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  77. CUA-bench — evaluation methodology and results ↗

    Vals AI · 2026

  78. CyberBench — evaluation methodology and results ↗

    Vals AI · 2026

  79. Excel Modeling Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  80. Excel Modeling Benchmark — evaluation methodology and results ↗

    Vals AI · 2026

  81. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  82. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  83. Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  84. IOI — evaluation methodology and results ↗

    Vals AI · 2026

  85. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  86. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  87. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  88. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  89. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  90. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  91. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  92. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  93. MysteryMechanism — evaluation methodology and results ↗

    Vals AI · 2026

  94. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  95. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  96. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  97. Robo-bench — evaluation methodology and results ↗

    Vals AI · 2026

  98. Vals RSI Index — evaluation methodology and results ↗

    Vals AI · 2026

  99. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  100. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

  101. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

  102. SWE-bench Multimodal — evaluation methodology and results ↗

    Vals AI · 2026

  103. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  104. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  105. Terminal-Bench 4.0 — evaluation methodology and results ↗

    Vals AI · 2026

  106. Terminal-Bench-Science — evaluation methodology and results ↗

    Vals AI · 2026

  107. Time Horizon Index: KSP — evaluation methodology and results ↗

    Vals AI · 2026

  108. Vibe Code Bench 1-100 — evaluation methodology and results ↗

    Vals AI · 2026

  109. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Claude Fable 5.1 · Claude Fable 5.1 (Max, Default Fallback) · Claude Fable 5.1 (Mini-SWE-agent) · Claude Fable 5.1 (OpenHands) · Claude Fable 5.1 (high) · Claude Fable 5.1 (low) · Claude Fable 5.1 (max) · Claude Fable 5.1 (max, with fallback) · Claude Fable 5.1 (medium) · Claude Fable 5.1 (xhigh) · Claude-Fable-5.1 · Fable 5.1 · Fable 5.1 (Claude Code) high · Fable 5.1 (max) · Fable 5.1 xhigh · Fable-5.1 · Fable-5.1 (Claude Code) xHigh · claude-fable-5-1 · claude-fable-5.1