Compare Models
Select models (max 5)
Claude Fable 5.1Mistral Large 4
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 65.83%±1.11 | 48.05%±1.11 |
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | 31.73%±3.23 |
| Finance Agent (v2)Core financial analyst tasks | 58.88%±2.06 | 54.68%±0.58 |
| Tax Agent BenchAgentic US corporate tax research | 77.64%±2.83 | 63.29%±3.23 |
| MedCodeMedical billing code support | 53.51%±2.17 | 40.69%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 40.00%±5.90 | N/A |
| Code MigrationRewriting programs in new languages | 54.61%±4.81 | 30.56%±4.22 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 58.08%±3.31 | 22.73%±0.88 |
| Vibe Code Bench v1.1Building web apps from scratch | 90.26%±1.57 | 78.40%±3.55 |
Benchmarks
Vals Index *
Claude Fable 5.1
0.00%± 1.11
(44/44)Mistral Large 4
0.00%± 1.11
(44/44)Legal Research Bench *
Claude Fable 5.1
0.00%± 3.46
(74/74)Mistral Large 4
0.00%± 3.23
(74/74)Finance Agent (v2) *
Claude Fable 5.1
0.00%± 2.06
(75/75)Mistral Large 4
0.00%± 0.58
(75/75)Tax Agent Bench *
Claude Fable 5.1
0.00%± 2.83
(66/66)Mistral Large 4
0.00%± 3.23
(66/66)MedCode *
Claude Fable 5.1
0.00%± 2.17
(105/105)Mistral Large 4
0.00%± 2.17
(105/105)Terminal-Bench Science
Claude Fable 5.1
0.00%± 5.90
(38/38)Mistral Large 4
N/ACode Migration *
Claude Fable 5.1
0.00%± 4.81
(74/74)Mistral Large 4
0.00%± 4.22
(74/74)Terminal-Bench 4.0
Claude Fable 5.1
0.00%± 3.31
(44/44)Mistral Large 4
0.00%± 0.88
(44/44)Vibe Code Bench v1.1 *
Claude Fable 5.1
0.00%± 1.57
(109/109)Mistral Large 4
0.00%± 3.55
(109/109)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-06
Comparison by Industry
Model performance on different sections of the economy.
Legal
50.16%
vs.23.78%
Finance
71.99%
vs.58.06%
Healthcare
72.40%
vs.60.56%
Math
100.00%
vs.10.00%
Science
43.87%
vs.39.60%
Academic
92.15%
vs.N/A
Education
48.53%
vs.N/A
Coding
60.10%
vs.38.25%
Cyber
46.66%
vs.N/A
Social Mobility
74.90%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$28.71
$13.78
Cost / TestVals Index
$28.71
vs.$13.78
Input Cost/ 1M Tokens
$10.00
vs.$1.36
Input Cache Write/ 1M Tokens
$12.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.25
vs.$0.14
Output Cost/ 1M Tokens
$50.00
vs.$4.18
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Mistral AI |
| Latency | 4611.98s | 6350.41s |
| Cost (In/Out) | $10 / $50 | $1.36 / $4.18 |
| Context Window | 1M | 512k |
| Max Output Token | 128k | 256k |
| Input Modality |