- Rank
- #379
- Total Output Tokens
- 2,169
- Response Time (avg)
- 2.83s
- Total Cost
- $0.008
Trinity Large Preview (default) vs Mercury 2.5
Trinity Large Preview (default) leads on average score with 4.4 vs 4.1. Trinity Large Preview (default) has the lower benchmark cost at $0.008 vs $0.026. Trinity Large Preview (default) is faster at 2.83s vs 5.10s, with pass rates of 20.3% vs 24.6%.
Compared models
- Rank
- #388
- Total Output Tokens
- 89,958
- Response Time (avg)
- 5.10s
- Total Cost
- $0.026
Recommended model
Trinity Large Preview (default)
It has the best score here (4.4), while costing about 3.3x less than Mercury 2.5.
Detailed comparison
| Metric | Trinity Large Preview Trinity Large Preview default Free Available | Mercury 2.5 Mercury 2.5 none |
|---|---|---|
| Score | 4.4 | 4.1 |
| Rank | #379 | #388 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.0 | 7.6 |
| Attempts | 66/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 20.3% | 24.6% |
| Flaky tests | 2 | 7 |
| Total Runs | 66 | 69 |
| Cost per result | 0.017 | 1.298 |
| Total Cost | $0.008 | $0.026 |
| Input Price | $0.243 / 1M | $0.040 / 1M |
| Output Price | $0.243 / 1M | $0.150 / 1M |
| Cache Read Price | N/A | $0.004 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 29,828 | 311,488 |
| Output Tokens | 2,169 | 89,958 |
| Reasoning Tokens | 0 | 0 |
| Response Time (avg) | 2.83s | 5.10s |
| Response Time (max) | 14.34s | 63.41s |
| Response Time (total) | 56.65s | 117.24s |
| Parameters | 398B total (13B active) | ~100B |
| Availability | Open source | 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.
#379 Trinity Large Preview
default
No endpoints found for arcee-ai/trinity-large-preview:free.
- Cost
- $0.000
- Time
- 0.0s
- Tokens
- 0 tok
#388 Mercury 2.5
none- Cost
- $0.001
- Time
- 2.7s
- Tokens
- 2,749 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.0 | 10.0 | 0.0% | 0 | 88ms | 0 | 0 | 0 | |
| Mercury 2.5 | 5.0 | 10.0 | 0.0% | 0 | 63.41s | 187,748 | 18,815 | 0 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.1 | 10.0 | 0.0% | 0 | 2.07s | 651 | 550 | 0 | |
| Mercury 2.5 | 3.8 | 8.3 | 16.7% | 1 | 469ms | 808 | 310 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.7 | 7.7 | 11.1% | 1 | 14.34s | 738 | 397 | 0 | |
| Mercury 2.5 | 3.7 | 7.0 | 22.2% | 1 | 12.50s | 7,888 | 61,297 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 1.5 | 5.0 | 0.0% | 0 | 8.91s | 12,053 | 294 | 0 | |
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 3.24s | 94,347 | 7,982 | 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 Preview | 10.0 | 10.0 | 100.0% | 0 | 3.26s | 6,900 | 186 | 0 | |
| Mercury 2.5 | 2.8 | 1.7 | 33.3% | 2 | 885ms | 8,352 | 754 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 5.3 | 10.0 | 33.3% | 0 | 877ms | 738 | 25 | 0 | |
| Mercury 2.5 | 5.3 | 7.2 | 44.4% | 1 | 533ms | 872 | 49 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 4.5 | 10.0 | 0.0% | 0 | 873ms | 498 | 104 | 0 | |
| Mercury 2.5 | 4.3 | 9.9 | 0.0% | 0 | 438ms | 540 | 138 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.5 | 10.0 | 0.0% | 0 | 822ms | 678 | 63 | 0 | |
| Mercury 2.5 | 4.9 | 6.9 | 33.3% | 1 | 493ms | 758 | 69 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.6 | 7.7 | 11.1% | 1 | 1.97s | 669 | 265 | 0 | |
| Mercury 2.5 | 3.7 | 7.2 | 22.2% | 1 | 515ms | 788 | 250 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 10.0 | 10.0 | 100.0% | 0 | 6.67s | 6,699 | 267 | 0 | |
| Mercury 2.5 | 10.0 | 10.0 | 100.0% | 0 | 1.23s | 9,150 | 275 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Trinity Large Preview | 3.0 | 10.0 | 0.0% | 0 | 777ms | 204 | 18 | 0 | |
| Mercury 2.5 | 3.0 | 10.0 | 0.0% | 0 | 384ms | 237 | 19 | 0 |
Quick Compare
Switch Comparison Pair
Trinity Large PreviewdefaultFree AvailablevsGranite 4.2 8BnoneTrinity Large PreviewdefaultFree AvailablevsNemotron 3 SupernoneFree AvailableTrinity Large PreviewdefaultFree AvailablevsCobuddymediumFree AvailableTrinity Large PreviewdefaultFree AvailablevsMercury 2noneMercury 2.5nonevsQwen3.5-9BmediumMercury 2.5nonevsGLM 4.7 FlashmediumTrinity Large PreviewdefaultFree AvailablevsMiniMax M2.5mediumTrinity Large PreviewdefaultFree AvailablevsNemotron 3.5 LightninglowFree AvailableTrinity Large PreviewdefaultFree AvailablevsLaguna S 2.1lowFree AvailableMercury 2.5nonevsMiniMax M2.5mediumTrinity Large PreviewdefaultFree AvailablevsGPT-5.4 NanononeTrinity Large PreviewdefaultFree AvailablevsDeepSeek V3.2none