- Rank
- #94
- Total Output Tokens
- 63,226
- Response Time (avg)
- 14.73s
- Total Cost
- $5.083
Claude Fable 5.2 (high) vs ERNIE-Light-DT-1.0 (high)
The average score is effectively tied at 8.7 vs 8.6. ERNIE-Light-DT-1.0 (high) has the lower benchmark cost at $1.027 vs $5.083. Claude Fable 5.2 (high) is faster at 14.73s vs 25.66s, with pass rates of 87.0% vs 75.4%.
Compared models
- Rank
- #97
- Total Output Tokens
- 194,474
- Response Time (avg)
- 25.66s
- Total Cost
- $1.027
Recommended model
ERNIE-Light-DT-1.0 (high)
It has the best score here (8.6), while costing about 5.0x less than Claude Fable 5.2 (high).
Detailed comparison
| Metric | Claude Fable 5.2 Claude Fable 5.2 high | ERNIE-Light-DT-1.0 ERNIE-Light-DT-1.0 high |
|---|---|---|
| Score | 8.7 | 8.6 |
| Rank | #94 | #97 |
| Reliability | 9.6 | 9.3 |
| Consistency | 9.3 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 87.0% | 75.4% |
| Flaky tests | 2 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 26.752 | 6.418 |
| Total Cost | $5.083 | $1.027 |
| Input Price | $8.000 / 1M | $1.130 / 1M |
| Output Price | $40.000 / 1M | $3.941 / 1M |
| Cache Read Price | $0.200 / 1M | $0.113 / 1M |
| Cache Write Price | $10.000 / 1M | N/A |
| Total Input Tokens | 319,219 | 230,563 |
| Output Tokens | 10,244 | 6,576 |
| Reasoning Tokens | 52,982 | 187,898 |
| Response Time (avg) | 14.73s | 25.66s |
| Response Time (max) | 84.72s | 200.80s |
| Response Time (total) | 338.82s | 590.18s |
| Parameters | ~9.5T total (~878B active) | ~320B total (~18B active) |
| Availability | Closed | Closed |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#94 Claude Fable 5.2
high- Cost
- $0.701
- Time
- 204.4s
- Tokens
- 17,664 tok
#97 ERNIE-Light-DT-1.0
high- Cost
- $0.067
- Time
- 129.8s
- Tokens
- 16,960 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 56.30s | 172,307 | 2,295 | 3,837 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 52.84s | 128,875 | 1,210 | 3,884 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 3.77s | 858 | 221 | 638 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 1.89s | 639 | 266 | 486 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 6.0 | 7.4 | 55.6% | 1 | 8.21s | 10,608 | 558 | 4,605 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 14.96s | 7,317 | 419 | 16,035 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 29.95s | 107,035 | 5,594 | 9,365 | |
| ERNIE-Light-DT-1.0 | 6.5 | 10.0 | 50.0% | 0 | 27.93s | 76,694 | 3,454 | 16,156 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 4.68s | 10,515 | 312 | 473 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 1.72s | 7,149 | 210 | 246 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 7.7 | 10.0 | 66.7% | 0 | 41.00s | 990 | 59 | 30,316 | |
| ERNIE-Light-DT-1.0 | 3.6 | 7.2 | 22.2% | 1 | 134.82s | 759 | 220 | 149,271 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 5.07s | 714 | 303 | 295 | |
| ERNIE-Light-DT-1.0 | 6.5 | 3.4 | 66.7% | 1 | 2.02s | 498 | 185 | 309 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 5.04s | 921 | 97 | 525 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 2.04s | 678 | 72 | 166 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 3.81s | 912 | 373 | 462 | |
| ERNIE-Light-DT-1.0 | 7.7 | 10.0 | 66.7% | 0 | 2.16s | 672 | 291 | 311 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 16.71s | 14,095 | 412 | 1,597 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 4.33s | 7,075 | 231 | 149 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 2.8 | 1.6 | 33.3% | 1 | 7.23s | 264 | 20 | 869 | |
| ERNIE-Light-DT-1.0 | 3.0 | 10.0 | 0.0% | 0 | 4.23s | 207 | 18 | 885 |
Quick Compare
Switch Comparison Pair
Claude Fable 5.2highvsGPT-6 SollowERNIE-Light-DT-1.0highvsMuse EmbermaxERNIE-Light-DT-1.0highvsMuse EmberlowERNIE-Light-DT-1.0highvsDeepSeek V4.1 FlashmaxClaude Fable 5.2highvsSeed 2.1 TurbomediumClaude Fable 5.2highvsMiMo-V2.6-PromediumClaude Fable 5.2highvsMuse EmberlowClaude Fable 5.2highvsMuse EmbermaxClaude Fable 5.2highvsGPT-5.2mediumERNIE-Light-DT-1.0highvsGPT-6 SollowClaude Fable 5.2highvsDeepSeek V4.1 FlashmaxERNIE-Light-DT-1.0highvsGPT-6.1 Terranone