Compare Models
Select models (max 7)
Claude Haiku 5.5GLM 5.3
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 58.71%±1.28 | 59.73%±1.11 |
| Legal Research BenchAgentic US legal research | 43.27%±3.44 | 49.04%±3.48 |
| Finance Agent v2.1Core financial analyst tasks | 65.37%±2.06 | 65.00%±2.01 |
| Tax Agent BenchAgentic US corporate tax research | 31.92%±3.35 | 39.70%±3.52 |
| MedCodeMedical billing code support | 51.54%±2.17 | 42.86%±2.11 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 10.00%±3.61 | 5.71%±2.79 |
| Code Migration v1.1Rewriting programs in new languages | 52.36%±3.49 | 55.07%±2.12 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 36.36%±2.31 | 38.89%±1.82 |
| Vibe Code Bench v1.1Building web apps from scratch | 90.44%±1.73 | 78.13%±3.94 |
Benchmarks
Vals Index *
Claude Haiku 5.5
0.00%± 1.28
(26/26)GLM 5.3
0.00%± 1.11
(26/26)Legal Research Bench *
Claude Haiku 5.5
0.00%± 3.44
(84/84)GLM 5.3
0.00%± 3.48
(84/84)Finance Agent v2.1 *
Claude Haiku 5.5
0.00%± 2.06
(30/30)GLM 5.3
0.00%± 2.01
(30/30)Tax Agent Bench *
Claude Haiku 5.5
0.00%± 3.35
(75/75)GLM 5.3
0.00%± 3.52
(75/75)MedCode *
Claude Haiku 5.5
0.00%± 2.17
(107/107)GLM 5.3
0.00%± 2.11
(107/107)Terminal-Bench-Science
Claude Haiku 5.5
0.00%± 3.61
(42/42)GLM 5.3
0.00%± 2.79
(42/42)Code Migration v1.1 *
Claude Haiku 5.5
0.00%± 3.49
(28/28)GLM 5.3
0.00%± 2.12
(28/28)Terminal-Bench 4.0
Claude Haiku 5.5
0.00%± 2.31
(54/54)GLM 5.3
0.00%± 1.82
(54/54)Vibe Code Bench v1.1 *
Claude Haiku 5.5
0.00%± 1.73
(118/118)GLM 5.3
0.00%± 3.94
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
23.72%
vs.49.49%
Finance
65.69%
vs.61.54%
Healthcare
70.54%
vs.65.84%
Math
89.00%
vs.49.00%
Science
38.50%
vs.14.34%
Academic
N/A
vs.87.45%
Education
45.78%
vs.N/A
Coding
41.90%
vs.53.94%
Cyber
40.60%
vs.40.62%
Social Mobility
63.19%
vs.68.54%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.173
$8.525
Cost / TestVals Index
$3.173
vs.$8.525
Input Cost/ 1M Tokens
$0.10
vs.$1.40
Input Cache Write/ 1M Tokens
$0.125
vs.N/A
Input Cache Read/ 1M Tokens
$0.01
vs.$0.26
Output Cost/ 1M Tokens
$0.50
vs.$4.40
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | zAI |
| Latency | 2988.33s | 3864.09s |
| Cost (In/Out) | $0.1 / $0.5 | $1.4 / $4.4 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |