- Rank
- #345
- Total Output Tokens
- 717,762
- Response Time (avg)
- 74.52s
- Total Cost
- $0.794
Trinity Large Thinking (high) vs ERNIE-Light-DT-1.0
Trinity Large Thinking (high) leads on average score with 5.7 vs 5.6. ERNIE-Light-DT-1.0 has the lower benchmark cost at $0.524 vs $0.794. ERNIE-Light-DT-1.0 is faster at 24.16s vs 74.52s, with pass rates of 42.0% vs 36.2%.
Compared models
- Rank
- #357
- Total Output Tokens
- 76,149
- Response Time (avg)
- 24.16s
- Total Cost
- $0.524
Recommended model
ERNIE-Light-DT-1.0
Its score stays close to the best score here (5.6 vs 5.7), while costing about 1.5x less than Trinity Large Thinking (high).
Detailed comparison
| Metric | Trinity Large Thinking Trinity Large Thinking high | ERNIE-Light-DT-1.0 ERNIE-Light-DT-1.0 none |
|---|---|---|
| Score | 5.7 | 5.6 |
| Rank | #345 | #357 |
| Reliability | 10.0 | 9.2 |
| Consistency | 7.3 | 9.7 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 42.0% | 36.2% |
| Flaky tests | 8 | 1 |
| Total Runs | 69 | 69 |
| Cost per result | 11.289 | 6.545 |
| Total Cost | $0.794 | $0.524 |
| Input Price | $0.250 / 1M | $1.130 / 1M |
| Output Price | $0.800 / 1M | $3.941 / 1M |
| Cache Read Price | $0.060 / 1M | $0.113 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 283,116 | 197,790 |
| Output Tokens | 277,920 | 76,149 |
| Reasoning Tokens | 665,124 | 0 |
| Response Time (avg) | 74.52s | 24.16s |
| Response Time (max) | 510.21s | 449.96s |
| Response Time (total) | 1713.90s | 555.78s |
| Parameters | 398B total (13B active) | ~320B total (~18B active) |
| Availability | Weights available | 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.
#345 Trinity Large Thinking
high- Cost
- $0.028
- Time
- 130.1s
- Tokens
- 34,387 tok
#357 ERNIE-Light-DT-1.0
none- Cost
- $0.009
- Time
- 14.9s
- Tokens
- 2,144 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 10.0 | 10.0 | 100.0% | 0 | 44.97s | 181,340 | 1,553 | 8,872 | |
| ERNIE-Light-DT-1.0 | 5.0 | 10.0 | 0.0% | 0 | 49.88s | 111,179 | 910 | 0 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 6.7 | 8.1 | 58.3% | 1 | 4.13s | 663 | 3,108 | 7,565 | |
| ERNIE-Light-DT-1.0 | 5.3 | 10.0 | 25.0% | 0 | 1.68s | 651 | 665 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 3.7 | 4.7 | 33.3% | 2 | 245.04s | 7,204 | 83,616 | 266,836 | |
| ERNIE-Light-DT-1.0 | 4.3 | 7.4 | 11.1% | 1 | 151.72s | 6,005 | 68,639 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 3.0 | 10.0 | 0.0% | 0 | 262.39s | 76,626 | 14,706 | 149,243 | |
| ERNIE-Light-DT-1.0 | 3.0 | 10.0 | 0.0% | 0 | 10.41s | 63,086 | 4,968 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 6.3 | 5.8 | 66.7% | 1 | 13.98s | 6,906 | 580 | 9,338 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 1.36s | 7,155 | 204 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 2.9 | 7.2 | 11.1% | 1 | 66.94s | 756 | 163,364 | 166,091 | |
| ERNIE-Light-DT-1.0 | 5.3 | 10.0 | 33.3% | 0 | 1.25s | 768 | 24 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 6.5 | 3.4 | 66.7% | 1 | 12.90s | 501 | 5,700 | 5,942 | |
| ERNIE-Light-DT-1.0 | 5.3 | 10.0 | 0.0% | 0 | 1.44s | 501 | 159 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 6.3 | 10.0 | 50.0% | 0 | 4.12s | 684 | 88 | 2,853 | |
| ERNIE-Light-DT-1.0 | 6.5 | 10.0 | 50.0% | 0 | 1.27s | 684 | 63 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 4.7 | 5.2 | 33.3% | 2 | 3.84s | 678 | 2,566 | 3,368 | |
| ERNIE-Light-DT-1.0 | 7.7 | 10.0 | 66.7% | 0 | 1.54s | 681 | 277 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 10.0 | 10.0 | 100.0% | 0 | 5.96s | 7,551 | 282 | 1,440 | |
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 6.15s | 6,870 | 222 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Thinking | 3.0 | 10.0 | 0.0% | 0 | 125.13s | 207 | 2,357 | 43,576 | |
| ERNIE-Light-DT-1.0 | 3.0 | 10.0 | 0.0% | 0 | 1.98s | 210 | 18 | 0 |
Quick Compare
Switch Comparison Pair
Trinity Large ThinkinghighvsRing 2.6 1tmediumTrinity Large ThinkinghighvsGPT-5 NanomediumERNIE-Light-DT-1.0nonevsStep 5 PreviewlowTrinity Large ThinkinghighvsGPT-5.4 MininoneTrinity Large ThinkinghighvsMistral Large 4noneTrinity Large ThinkinghighvsSeed 2.1 TurbononeTrinity Large ThinkinghighvsHy4noneTrinity Large ThinkinghighvsDots 3 Note PreviewmediumFree AvailableTrinity Large ThinkinghighvsDeepSeek V4.1 FlashnoneERNIE-Light-DT-1.0nonevsSpace Bunny AlphalowTrinity Large ThinkinghighvsGPT-5.6 TerranoneTrinity Large ThinkinghighvsGemma 4 31BnoneFree Available