Compare Models
Select models (max 7)
Claude Opus 5GLM 5.3
 |  |  |
|---|---|---|
| SWE-benchReal software engineering tasks | 97.00%±0.76 | 95.40%±0.94 |
Benchmarks
SWE-bench
Claude Opus 5
0.00%± 0.76
(88/88)GLM 5.3
0.00%± 0.94
(88/88)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-09
Comparison by Industry
Model performance on different sections of the economy.
Legal
71.13%
vs.53.80%
Finance
64.77%
vs.62.45%
Healthcare
77.28%
vs.65.84%
Math
99.00%
vs.49.00%
Science
47.93%
vs.14.34%
Academic
91.64%
vs.87.45%
Coding
63.03%
vs.53.94%
Cyber
38.79%
vs.40.62%
Social Mobility
76.93%
vs.68.54%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$8.525
Cost / TestVals Index
N/A
vs.$8.525
Input Cost/ 1M Tokens
$5.00
vs.$1.40
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.$0.26
Output Cost/ 1M Tokens
$25.00
vs.$4.40
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | zAI |
| Latency | N/A | 3864.09s |
| Cost (In/Out) | $5 / $25 | $1.4 / $4.4 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |