Benchmark Almanac

Vals Index v2.2

Claude Fable 5.2 71.3% leads since November 2026
Claude Fable 5.2 71.3% leads since November 2026
In use
Version 2.2

The official leaderboard hasn’t scored a model released after Gemini 4 Neon (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 46.5%.

Agents are scored on eight finance, coding, legal, and tax benchmarks, combined with weights from each sector's share of US GDP.

Version 2.2 from 19 October 2026: (8.0 × finance + 5.6 × coding + 1.2 × legal + 0.5 × tax) / 15.3. Finance averages Finance Agent v2.1 and EMB v1.1. Coding averages Terminal-Bench 4, Vibe Code Bench v1.1 and Code Migration v1.1. Legal averages Legal Research and HLAB-Vals-1.1. Tax is Tax Agent Bench (all-pass accuracy). Six of the eight components are private. Earlier versions have their own records.

Made by
Vals AI
Released
October 2026
Kind
Composite work indices
Scored
Graded by a model
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
Interaction
Agentic
Environment
Terminal, APIs and tools
Items from
Another benchmark
Run by
A host
Based on
Vals Index v2.1
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 19th, 2026
42
Entries on its own leaderboard, 41 models we track
4
Launch posts list it, from 2 labs
3
System cards report it, from 2 labs

Claude Fable 5.2 leads with 71.3% Claude Fable 5.2 leads with 71.3%

Best score per entry from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

Claude Fable 5.2 leads with 71.3%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.

  1. 1 Claude Fable 5.2 71.3%
  2. 2 Gemini 4 Neon 70.9%
  3. 3 Claude Sonnet 5.5 70.8%
  4. 4 Gemini 4 Carbon 70.5%
  5. 5 Claude Opus 5.5 70.1%
  6. 6 Gemini 4 Argon 69.4%
  7. 7 Gemini 4 Hydrogen 68.5%
  8. 8 GPT-6.2 Astra 67.7%
  9. 9 Muse Wonder Full 66.8%
  10. 10 GPT-6.2 Sol 66.1%
  11. 11 GPT-6 Astra 65%
  12. 12 Muse Wonder 64.9%
  13. 13 GPT-6.1 Sol 63.9%
  14. 14 Qwen4-Max 63.2%
  15. 15 Kimi K3.1 Pro 62.5%
  16. 16 DeepSeek V4.1 Flash 1017 61.3%
  17. 17 GPT-6.1 Terra 60.5%
  18. 18 Muse Ember 60.5%
  19. 19 GLM-5.3 59.9%
  20. 20 Tencent Hy4 59.4%
  21. 21 Qwen3.8 Max (0902) 59%
  22. 22 Claude Haiku 5.5 58.7%
  23. 23 Grok 4.7 58.6%
  24. 24 MiMo-V2.6 Pro 57.8%
  25. 25 Mistral Large 4 56.5%
  26. 26 Inkling 2 Small 56.1%
  27. 27 Gemini 3.8 Flash 56%
  28. 28 MiMo-V2.6 Flash 54.8%
  29. 29 Step 5 Preview 54.8%
  30. 30 MiniMax-M3.1-Flash 53.8%
  31. 31 Tencent Hy4 preview 53.2%
  32. 32 DeepSeek V4 Pro 0813 53%
  33. 33 Kimi K3 53%
  34. 34 GPT-6 Luna 52.3%
  35. 35 GLM-5.3-Flash 50.9%
  36. 36 Hy4 Flash 50.8%
  37. 37 Muse Spark Open 48.6%
  38. 38 Mercury 3 43.7%
  39. 39 Beam 1.0 43.4%
  40. 40 Nemotron 3.5 Super VL 29.8%
  41. 41 Inkling 29%
  42. 42 Inkling-Small 27.6%

Source: Official Vals Index v2.2 leaderboard

Source: Official Vals Index v2.2 leaderboard

Sources: Official Vals Index v2.2 leaderboard and labs’ model cards

#EntryScore ± 95% CISettingDateSource
1 Claude Fable 5.2 71.3% ±1.9 Nov 2026 Official leaderboard
2 Gemini 4 Neon 70.9% ±1.8 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 70.8% ±1.8 Sep 2026 Official leaderboard
4 Gemini 4 Carbon 70.5% ±1.9 Oct 2026 Official leaderboard
5 Claude Opus 5.5 70.1% ±2 Sep 2026 Official leaderboard
6 Gemini 4 Argon 69.4% ±2.1 Sep 2026 Official leaderboard
7 Gemini 4 Hydrogen 68.5% ±1.9 Nov 2026 Official leaderboard
8 GPT-6.2 Astra 67.7% ±1.8 Nov 2026 Official leaderboard
9 Muse Wonder Full 66.8% ±2.1 Oct 2026 Official leaderboard
10 GPT-6.2 Sol 66.1% ±1.8 Nov 2026 Official leaderboard
11 GPT-6 Astra 65% ±2.2 Sep 2026 Official leaderboard
12 Muse Wonder 64.9% ±2.1 Oct 2026 Official leaderboard
13 GPT-6.1 Sol 63.9% ±2.1 Sep 2026 Official leaderboard
14 Qwen4-Max 63.2% ±2 Nov 2026 Official leaderboard
15 Kimi K3.1 Pro 62.5% ±2.2 Oct 2026 Official leaderboard
16 DeepSeek V4.1 Flash 1017 61.3% ±2.1 Oct 2026 Official leaderboard
17 GPT-6.1 Terra 60.5% ±1.9 Oct 2026 Official leaderboard
18 Muse Ember 60.5% ±2.1 Nov 2026 Official leaderboard
19 GLM-5.3 59.9% ±2.2 Aug 2026 Official leaderboard
20 Tencent Hy4 59.4% ±2.1 Nov 2026 Official leaderboard
21 Qwen3.8 Max (0902) 59% ±2.1 Sep 2026 Official leaderboard
22 Claude Haiku 5.5 58.7% ±2.5 Oct 2026 Official leaderboard
23 Grok 4.7 58.6% ±2 Sep 2026 Official leaderboard
24 MiMo-V2.6 Pro 57.8% ±2.4 Sep 2026 Official leaderboard
25 Mistral Large 4 56.5% ±2.5 Oct 2026 Official leaderboard
26 Inkling 2 Small 56.1% ±2.3 Nov 2026 Official leaderboard
27 Gemini 3.8 Flash 56% ±2.2 Sep 2026 Official leaderboard
28 MiMo-V2.6 Flash 54.8% ±2.2 Sep 2026 Official leaderboard
29 Step 5 Preview 54.8% ±2.3 Sep 2026 Official leaderboard
30 MiniMax-M3.1-Flash 53.8% ±2.1 Oct 2026 Official leaderboard
31 Tencent Hy4 preview 53.2% ±2.2 Aug 2026 Official leaderboard
32 DeepSeek V4 Pro 0813 53% ±2 Aug 2026 Official leaderboard
33 Kimi K3 53% ±2 Jul 2026 Official leaderboard
34 GPT-6 Luna 52.3% ±2.2 Sep 2026 Official leaderboard
35 GLM-5.3-Flash 50.9% ±2.5 Aug 2026 Official leaderboard
36 Hy4 Flash 50.8% ±2.1 Official leaderboard
37 Muse Spark Open 48.6% ±2.1 Oct 2026 Official leaderboard
38 Mercury 3 43.7% ±2.4 Oct 2026 Official leaderboard
39 Beam 1.0 43.4% ±2.1 Oct 2026 Official leaderboard
40 Nemotron 3.5 Super VL 29.8% ±2 Oct 2026 Official leaderboard
41 Inkling 29% ±2.2 Jul 2026 Official leaderboard
42 Inkling-Small 27.6% ±2.2 Jul 2026 Official leaderboard
#ModelScore ± 95% CISettingDateSource
1 Claude Fable 5.2 71.3% ±1.9 Nov 2026 Official leaderboard
2 Gemini 4 Neon 70.9% ±1.8 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 70.8% ±1.8 Sep 2026 Official leaderboard
4 Gemini 4 Carbon 70.5% ±1.9 Oct 2026 Official leaderboard
5 Claude Opus 5.5 70.1% ±2 Sep 2026 Official leaderboard
6 Gemini 4 Argon 69.4% ±2.1 Sep 2026 Official leaderboard
7 Gemini 4 Hydrogen 68.5% ±1.9 Nov 2026 Official leaderboard
8 GPT-6.2 Astra 67.7% ±1.8 Nov 2026 Official leaderboard
9 Muse Wonder Full 66.8% ±2.1 Oct 2026 Official leaderboard
10 GPT-6.2 Sol 66.1% ±1.8 Nov 2026 Official leaderboard
11 GPT-6 Astra 65% ±2.2 Sep 2026 Official leaderboard
12 Muse Wonder 64.9% ±2.1 Oct 2026 Official leaderboard
13 GPT-6.1 Sol 63.9% ±2.1 Sep 2026 Official leaderboard
14 Qwen4-Max 63.2% ±2 Nov 2026 Official leaderboard
15 Kimi K3.1 Pro 62.5% ±2.2 Oct 2026 Official leaderboard
16 DeepSeek V4.1 Flash 1017 61.3% ±2.1 Oct 2026 Official leaderboard
17 GPT-6.1 Terra 60.5% ±1.9 Oct 2026 Official leaderboard
18 Muse Ember 60.5% ±2.1 Nov 2026 Official leaderboard
19 GLM-5.3 59.9% ±2.2 Aug 2026 Official leaderboard
20 Tencent Hy4 59.4% ±2.1 Nov 2026 Official leaderboard
21 Qwen3.8 Max (0902) 59% ±2.1 Sep 2026 Official leaderboard
22 Claude Haiku 5.5 58.7% ±2.5 Oct 2026 Official leaderboard
23 Grok 4.7 58.6% ±2 Sep 2026 Official leaderboard
24 MiMo-V2.6 Pro 57.8% ±2.4 Sep 2026 Official leaderboard
25 Mistral Large 4 56.5% ±2.5 Oct 2026 Official leaderboard
26 Inkling 2 Small 56.1% ±2.3 Nov 2026 Official leaderboard
27 Gemini 3.8 Flash 56% ±2.2 Sep 2026 Official leaderboard
28 MiMo-V2.6 Flash 54.8% ±2.2 Sep 2026 Official leaderboard
29 Step 5 Preview 54.8% ±2.3 Sep 2026 Official leaderboard
30 MiniMax-M3.1-Flash 53.8% ±2.1 Oct 2026 Official leaderboard
31 Tencent Hy4 preview 53.2% ±2.2 Aug 2026 Official leaderboard
32 DeepSeek V4 Pro 0813 53% ±2 Aug 2026 Official leaderboard
33 Kimi K3 53% ±2 Jul 2026 Official leaderboard
34 GPT-6 Luna 52.3% ±2.2 Sep 2026 Official leaderboard
35 GLM-5.3-Flash 50.9% ±2.5 Aug 2026 Official leaderboard
36 Muse Spark Open 48.6% ±2.1 Oct 2026 Official leaderboard
37 Mercury 3 43.7% ±2.4 Oct 2026 Official leaderboard
38 Beam 1.0 43.4% ±2.1 Oct 2026 Official leaderboard
39 Nemotron 3.5 Super VL 29.8% ±2 Oct 2026 Official leaderboard
40 Inkling 29% ±2.2 Jul 2026 Official leaderboard
41 Inkling-Small 27.6% ±2.2 Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 71.3% Nov 2026 Official leaderboard
2 Gemini 4 Neon 70.9% Nov 2026 Lab model card
3 Claude Sonnet 5.5 70.8% Sep 2026 Official leaderboard
4 Gemini 4 Carbon 70.5% Oct 2026 Official leaderboard
5 Claude Opus 5.5 70.1% Sep 2026 Official leaderboard
6 Gemini 4 Argon 69.4% Sep 2026 Official leaderboard
7 Gemini 4 Hydrogen 68.5% Nov 2026 Official leaderboard
8 GPT-6.2 Astra 67.7% Nov 2026 Official leaderboard
9 Muse Wonder Full 66.8% Oct 2026 Official leaderboard
10 GPT-6.2 Sol 66.1% Nov 2026 Official leaderboard
11 GPT-6 Astra 65% Sep 2026 Official leaderboard
12 Muse Wonder 64.9% Oct 2026 Official leaderboard
13 GPT-6.1 Sol 63.9% Sep 2026 Official leaderboard
14 Qwen4-Max 63.2% Nov 2026 Official leaderboard
15 Kimi K3.1 Pro 62.5% Oct 2026 Official leaderboard
16 DeepSeek V4.1 Flash 1017 61.3% Oct 2026 Official leaderboard
17 GPT-6.1 Terra 60.5% Oct 2026 Official leaderboard
18 Muse Ember 60.5% Nov 2026 Official leaderboard
19 GLM-5.3 59.9% Aug 2026 Official leaderboard
20 Tencent Hy4 59.4% Nov 2026 Official leaderboard
21 Qwen3.8 Max (0902) 59% Sep 2026 Official leaderboard
22 Claude Haiku 5.5 58.7% Oct 2026 Official leaderboard
23 Grok 4.7 58.6% Sep 2026 Official leaderboard
24 MiMo-V2.6 Pro 57.8% Sep 2026 Official leaderboard
25 Mistral Large 4 56.5% Oct 2026 Official leaderboard
26 Inkling 2 Small 56.1% Nov 2026 Lab model card
27 Gemini 3.8 Flash 56% Sep 2026 Official leaderboard
28 MiMo-V2.6 Flash 54.8% Sep 2026 Official leaderboard
29 Step 5 Preview 54.8% Sep 2026 Official leaderboard
30 MiniMax-M3.1-Flash 53.8% Oct 2026 Official leaderboard
31 Tencent Hy4 preview 53.2% Aug 2026 Official leaderboard
32 DeepSeek V4 Pro 0813 53% Aug 2026 Official leaderboard
33 Kimi K3 53% Jul 2026 Official leaderboard
34 GPT-6 Luna 52.3% Sep 2026 Official leaderboard
35 GLM-5.3-Flash 50.9% Aug 2026 Official leaderboard
36 Muse Spark Open 48.6% Oct 2026 Official leaderboard
37 Inkling 2 Mini 46.5% Nov 2026 Lab model card
38 Mercury 3 43.7% Oct 2026 Official leaderboard
39 Beam 1.0 43.4% Oct 2026 Official leaderboard
40 Nemotron 3.5 Super VL 29.8% Oct 2026 Official leaderboard
41 Inkling 29% Jul 2026 Official leaderboard
42 Inkling-Small 27.6% Jul 2026 Official leaderboard

Labs report scores for 4 models in their cards. Switch the scores above to rank them together.

Accuracy against latency

The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.

0% 20% 40% 60% 80% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonMuse EmberBeam 1.0 0% 20% 40% 60% 80% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonMuse EmberBeam 1.0
ModelSettingAccuracyLatency (mean per test)
Claude Fable 5.2 71.3% 2,622 s
Gemini 4 Neon 70.9% 1,885 s
Claude Sonnet 5.5 70.9% 5,159 s
Gemini 4 Carbon 70.5% 2,865 s
Claude Opus 5.5 70.1% 5,071 s
Gemini 4 Argon 69.4% 2,698 s
Gemini 4 Hydrogen 68.5% 1,925 s
GPT-6.2 Astra 67.7% 3,136 s
Muse Wonder Full 66.8% 3,559 s
GPT-6.2 Sol 66.1% 2,507 s
GPT-6 Astra 65% 2,019 s
Muse Wonder 64.9% 2,124 s
GPT-6.1 Sol 63.9% 2,664 s
Qwen4-Max 63.2% 3,880 s
Kimi K3.1 Pro 62.5% 3,817 s
DeepSeek V4.1 Flash 1017 61.3% 2,395 s
GPT-6.1 Terra 60.5% 2,383 s
Muse Ember 60.5% 902.37 s
GLM-5.3 59.9% 3,864 s
Tencent Hy4 59.4% 3,092 s
Qwen3.8 Max (0902) 59.1% 6,346 s
Claude Haiku 5.5 58.7% 2,997 s
Grok 4.7 58.6% 2,014 s
MiMo-V2.6 Pro 57.8% 4,356 s
Mistral Large 4 56.5% 2,868 s
Inkling 2 Small 56.1% 3,035 s
Gemini 3.8 Flash 56% 2,159 s
MiMo-V2.6 Flash 54.8% 4,028 s
Step 5 Preview 54.8% 3,929 s
MiniMax-M3.1-Flash 53.8% 2,598 s
Tencent Hy4 preview 53.2% 3,563 s
DeepSeek V4 Pro 0813 53% 3,483 s
Kimi K3 53% 4,496 s
GPT-6 Luna 52.3% 1,943 s
GLM-5.3-Flash 50.9% 3,831 s
Hy4 Flash 50.8% 1,019 s
Muse Spark Open 48.6% 4,925 s
Mercury 3 43.7% 1,326 s
Beam 1.0 43.4% 446.56 s
Nemotron 3.5 Super VL 29.8% 514.01 s
Inkling 29% 1,033 s
Inkling-Small 27.6% 986.44 s

Accuracy against latency

The Vals scatter chart with its x axis switched from Cost to Latency: mean time per test against accuracy, on a log scale. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.

0% 20% 40% 60% 80% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonMuse EmberBeam 1.0 0% 20% 40% 60% 80% 1001,00010K Latency (mean per test) (s), log scale, lower is better Accuracy Claude Fable 5.2Gemini 4 NeonMuse EmberBeam 1.0
ModelSettingAccuracyLatency (mean per test)
Claude Fable 5.2 71.3% 2,622 s
Gemini 4 Neon 70.9% 1,885 s
Claude Sonnet 5.5 70.9% 5,159 s
Gemini 4 Carbon 70.5% 2,865 s
Claude Opus 5.5 70.1% 5,071 s
Gemini 4 Argon 69.4% 2,698 s
Gemini 4 Hydrogen 68.5% 1,925 s
GPT-6.2 Astra 67.7% 3,136 s
Muse Wonder Full 66.8% 3,559 s
GPT-6.2 Sol 66.1% 2,507 s
GPT-6 Astra 65% 2,019 s
Muse Wonder 64.9% 2,124 s
GPT-6.1 Sol 63.9% 2,664 s
Qwen4-Max 63.2% 3,880 s
Kimi K3.1 Pro 62.5% 3,817 s
DeepSeek V4.1 Flash 1017 61.3% 2,395 s
GPT-6.1 Terra 60.5% 2,383 s
Muse Ember 60.5% 902.37 s
GLM-5.3 59.9% 3,864 s
Tencent Hy4 59.4% 3,092 s
Qwen3.8 Max (0902) 59.1% 6,346 s
Claude Haiku 5.5 58.7% 2,997 s
Grok 4.7 58.6% 2,014 s
MiMo-V2.6 Pro 57.8% 4,356 s
Mistral Large 4 56.5% 2,868 s
Inkling 2 Small 56.1% 3,035 s
Gemini 3.8 Flash 56% 2,159 s
MiMo-V2.6 Flash 54.8% 4,028 s
Step 5 Preview 54.8% 3,929 s
MiniMax-M3.1-Flash 53.8% 2,598 s
Tencent Hy4 preview 53.2% 3,563 s
DeepSeek V4 Pro 0813 53% 3,483 s
Kimi K3 53% 4,496 s
GPT-6 Luna 52.3% 1,943 s
GLM-5.3-Flash 50.9% 3,831 s
Muse Spark Open 48.6% 4,925 s
Mercury 3 43.7% 1,326 s
Beam 1.0 43.4% 446.56 s
Nemotron 3.5 Super VL 29.8% 514.01 s
Inkling 29% 1,033 s
Inkling-Small 27.6% 986.44 s

The best score, 71.3%, costs $18 a task

Runs on the cost frontier score higher than any run that's cheaper. Muse Wonder Full comes within 4.5 points of the best for $6.81 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Meta DeepSeek Anthropic OpenAI Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 Gemini 4 Neon Muse Wonder Full GPT-6.2 Sol DeepSeek V4.1 Flash 1017 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 DeepSeek V4.1 Flash 1017

Source: Official Vals Index v2.2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 71.3% $18 197,828
Gemini 4 Neon 70.9% $7.40 216,039
Claude Sonnet 5.5 70.8% $16 594,550
Gemini 4 Carbon 70.5% $11 205,620
Claude Opus 5.5 70.1% $25 455,040
Gemini 4 Argon 69.4% $13 159,229
Gemini 4 Hydrogen 68.5% $9.84 336,849
GPT-6.2 Astra 67.7% $11 90,655
Muse Wonder Full 66.8% $6.81 103,433
GPT-6.2 Sol 66.1% $3.18 102,959
GPT-6 Astra 65% $21 99,102
Muse Wonder 64.9% $11 115,812
GPT-6.1 Sol 63.9% $3.61 112,502
Qwen4-Max 63.2% $9.33 192,550
Kimi K3.1 Pro 62.5% $6.44 159,072
DeepSeek V4.1 Flash 1017 61.3% $0.66 258,045
GPT-6.1 Terra 60.5% $2.94 157,426
Muse Ember 60.5% $0.15 79,013
GLM-5.3 59.9% $8.52 202,266
Tencent Hy4 59.4% $1.72 238,203
Qwen3.8 Max (0902) 59% $8.73 231,724
Claude Haiku 5.5 58.7% $3.17 570,127
Grok 4.7 58.6% $12 124,146
MiMo-V2.6 Pro 57.8% $0.43 147,277
Mistral Large 4 56.5% $3.72 122,413
Inkling 2 Small 56.1% $3.51 281,311
Gemini 3.8 Flash 56% $5.03 130,206
MiMo-V2.6 Flash 54.8% $0.22 172,167
Step 5 Preview 54.8% $2.73 159,796
MiniMax-M3.1-Flash 53.8% $0.66 255,285
Tencent Hy4 preview 53.2% $1.57 160,621
DeepSeek V4 Pro 0813 53% $2.50 169,366
Kimi K3 53% $7.17 107,342
GPT-6 Luna 52.3% $0.45 170,502
GLM-5.3-Flash 50.9% $2.05 203,647
Muse Spark Open 48.6% $4.72 65,357
Mercury 3 43.7% $0.48 117,494
Beam 1.0 43.4% 41,553
Nemotron 3.5 Super VL 29.8% $0.63 96,498
Inkling 29% $1.85 64,607
Inkling-Small 27.6% $0.40 55,978

The best score, 71.3%, costs $18 a task

Runs on the cost frontier score higher than any run that's cheaper. Muse Wonder Full comes within 4.5 points of the best for $6.81 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Meta DeepSeek Anthropic OpenAI Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 Gemini 4 Neon Muse Wonder Full GPT-6.2 Sol DeepSeek V4.1 Flash 1017 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Claude Fable 5.2 DeepSeek V4.1 Flash 1017

Source: Official Vals Index v2.2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 71.3% $18 197,828
Gemini 4 Neon 70.9% $7.40 216,039
Claude Sonnet 5.5 70.8% $16 594,550
Gemini 4 Carbon 70.5% $11 205,620
Claude Opus 5.5 70.1% $25 455,040
Gemini 4 Argon 69.4% $13 159,229
Gemini 4 Hydrogen 68.5% $9.84 336,849
GPT-6.2 Astra 67.7% $11 90,655
Muse Wonder Full 66.8% $6.81 103,433
GPT-6.2 Sol 66.1% $3.18 102,959
GPT-6 Astra 65% $21 99,102
Muse Wonder 64.9% $11 115,812
GPT-6.1 Sol 63.9% $3.61 112,502
Qwen4-Max 63.2% $9.33 192,550
Kimi K3.1 Pro 62.5% $6.44 159,072
DeepSeek V4.1 Flash 1017 61.3% $0.66 258,045
GPT-6.1 Terra 60.5% $2.94 157,426
Muse Ember 60.5% $0.15 79,013
GLM-5.3 59.9% $8.52 202,266
Tencent Hy4 59.4% $1.72 238,203
Qwen3.8 Max (0902) 59% $8.73 231,724
Claude Haiku 5.5 58.7% $3.17 570,127
Grok 4.7 58.6% $12 124,146
MiMo-V2.6 Pro 57.8% $0.43 147,277
Mistral Large 4 56.5% $3.72 122,413
Inkling 2 Small 56.1% $3.51 281,311
Gemini 3.8 Flash 56% $5.03 130,206
MiMo-V2.6 Flash 54.8% $0.22 172,167
Step 5 Preview 54.8% $2.73 159,796
MiniMax-M3.1-Flash 53.8% $0.66 255,285
Tencent Hy4 preview 53.2% $1.57 160,621
DeepSeek V4 Pro 0813 53% $2.50 169,366
Kimi K3 53% $7.17 107,342
GPT-6 Luna 52.3% $0.45 170,502
GLM-5.3-Flash 50.9% $2.05 203,647
Muse Spark Open 48.6% $4.72 65,357
Mercury 3 43.7% $0.48 117,494
Beam 1.0 43.4% 41,553
Nemotron 3.5 Super VL 29.8% $0.63 96,498
Inkling 29% $1.85 64,607
Inkling-Small 27.6% $0.40 55,978

2 models have held number one on the official leaderboard since its release in October 2026 2 models have held number one with claims included since its release in October 2026

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.

Anthropic Google DeepMind
Own leaderboard 2 leaders
Lab claims 2 leaders

Sources: Official Vals Index v2.2 leaderboard and labs’ model cards

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Claude Fable 5.2 Claude Sonnet 5.5 GPT-6 Astra GLM-5.3 DeepSeek V4 Pro 0813 Inkling 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-6 Astra

Sources: Official Vals Index v2.2 leaderboard and labs’ model cards

2 labs put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out. Google DeepMind accounts for 3 of the 6 releases that named it since 2024.

Google DeepMind
Thinking Machines
DateLaunch postScoreAs the post writes it
Nov 20, 2026 Inkling 2 Mini 46.5 Vals Index (v2.2)
Nov 18, 2026 Gemini 4 Neon 70.9 Vals Index v2.2
Nov 5, 2026 Inkling 2 Small 56.1 Vals Index (v2.2)
Oct 28, 2026 Gemini 4 Carbon 70.4 Vals Index v2.2

3 system cards report it, from 2 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Nov 20, 2026 Inkling 2 Mini model card 46.5 Vals Index (v2.2) Capabilities
Nov 18, 2026 Gemini 4 Neon model card 70.9 Vals Index v2.2 (results table, p.4) Capabilities
Nov 10, 2026 Gemini 4 Carbon model card 70.4 Vals Index v2.2 (results table) Capabilities

3 lab claims next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 3 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Gemini 4 Carbon 70.4% Vals Index v2.2 70.5% Leaderboard Same
Gemini 4 Neon 70.9% Vals Index v2.2 70.9% Leaderboard Same
Inkling 2 Small 56.1% Vals Index (v2.2) 56.1% Leaderboard Same

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Anthropic OpenAI Google DeepMind
Vals Index v2.2 16 leaders
Vals Index v1 Replaced by 2, Aug 2026
Vals Index v2 Replaced by 2.1, Sep 2026

Source: Official leaderboards

More in Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 12 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (42 entries), launch posts (4 scores) and system cards (3 scores).
  • Pass Models scored 42 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
  • Pass Frontier models 9 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 71.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on vals.ai: 41 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 19th, 2026.
  • Pass Read worked The last read worked.
Consistency 2 pass
  • Pass Lab claims All 3 pairs agree within 10 points.
  • Pass Known issues No published audit found problems.

How we check