- Rank
- #224
- Total Output Tokens
- 180,597
- Response Time (avg)
- 7.61s
- Total Cost
- $0.040
Mercury 2.5 Preview (high) vs Beam 1.0 501B A23B (xhigh)
The average score is effectively tied at 6.5 vs 6.5. Mercury 2.5 Preview (high) has the lower benchmark cost at $0.040 vs $0.688. Mercury 2.5 Preview (high) is faster at 7.61s vs 9.18s, with pass rates of 65.2% vs 63.8%.
Compared models
- Rank
- #226
- Total Output Tokens
- 158,497
- Response Time (avg)
- 9.18s
- Total Cost
- $0.688
Recommended model
Mercury 2.5 Preview (high)
It has the best score here (6.5), while costing about 17.6x less than Beam 1.0 501B A23B (xhigh).
Detailed comparison
| Metric | Mercury 2.5 Preview Mercury 2.5 Preview high | Beam 1.0 501B A23B Beam 1.0 501B A23B xhigh |
|---|---|---|
| Score | 6.5 | 6.5 |
| Rank | #224 | #226 |
| Reliability | 9.9 | 10.0 |
| Consistency | 8.0 | 8.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 65.2% | 63.8% |
| Flaky tests | 6 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 0.319 | 5.730 |
| Total Cost | $0.040 | $0.688 |
| Input Price | $0.040 / 1M | $1.000 / 1M |
| Output Price | $0.150 / 1M | $3.000 / 1M |
| Cache Read Price | N/A | $0.100 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 298,512 | 212,065 |
| Output Tokens | 3,178 | 4,428 |
| Reasoning Tokens | 177,419 | 154,069 |
| Response Time (avg) | 7.61s | 9.18s |
| Response Time (max) | 86.84s | 44.64s |
| Response Time (total) | 175.08s | 211.12s |
| Parameters | ~100B | 501B total (23B active) |
| Availability | Closed | Open source |
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.
#224 Mercury 2.5 Preview
high- Cost
- $0.001
- Time
- 4.5s
- Tokens
- 3,851 tok
#226 Beam 1.0 501B A23B
xhigh- Cost
- $0.009
- Time
- 16.5s
- Tokens
- 6,827 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 6.1 | 3.1 | 66.7% | 1 | 86.84s | 182,753 | 616 | 16,476 | |
| Beam 1.0 501B A23B | 3.0 | 10.0 | 0.0% | 0 | 44.64s | 181,898 | 2,416 | 18,550 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 1.09s | 785 | 181 | 7,008 | |
| Beam 1.0 501B A23B | 9.2 | 8.4 | 91.7% | 1 | 1.52s | 1,125 | 355 | 3,764 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 6.7 | 7.8 | 55.6% | 1 | 6.13s | 7,751 | 485 | 42,569 | |
| Beam 1.0 501B A23B | 10.0 | 10.0 | 100.0% | 0 | 20.68s | 7,801 | 585 | 46,192 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 3.8 | 1.6 | 50.0% | 2 | 14.36s | 95,789 | 765 | 54,789 | |
| Beam 1.0 501B A23B | 3.0 | 10.0 | 0.0% | 0 | 2.68s | 7,671 | 132 | 2,097 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 2.24s | 8,292 | 560 | 8,522 | |
| Beam 1.0 501B A23B | 10.0 | 10.0 | 100.0% | 0 | 1.60s | 7,998 | 271 | 2,047 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 2.9 | 4.4 | 22.2% | 2 | 5.68s | 857 | 67 | 25,958 | |
| Beam 1.0 501B A23B | 5.9 | 7.2 | 55.6% | 1 | 20.22s | 1,122 | 72 | 59,707 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 5.1 | 10.0 | 0.0% | 0 | 1.88s | 542 | 94 | 3,300 | |
| Beam 1.0 501B A23B | 5.1 | 3.4 | 33.3% | 1 | 2.50s | 618 | 87 | 2,749 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 9.8 | 10.0 | 100.0% | 0 | 1.05s | 741 | 94 | 3,777 | |
| Beam 1.0 501B A23B | 9.8 | 10.0 | 100.0% | 0 | 1.15s | 925 | 90 | 1,631 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 1.21s | 774 | 292 | 6,066 | |
| Beam 1.0 501B A23B | 5.8 | 4.4 | 66.7% | 2 | 4.46s | 1,038 | 309 | 9,948 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 2.25s | 0 | 0 | 0 | |
| Beam 1.0 501B A23B | 3.0 | 10.0 | 0.0% | 0 | 1.84s | 1,533 | 72 | 465 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 5.41s | 228 | 24 | 8,954 | |
| Beam 1.0 501B A23B | 3.0 | 10.0 | 0.0% | 0 | 9.10s | 336 | 39 | 6,919 |
Quick Compare
Switch Comparison Pair
Mercury 2.5highvsBeam 1.0 501B A23BxhighBeam 1.0 501B A23BxhighvsGLM 5.3lowMercury 2.5 PreviewhighvsQwen3.6 35B A3BmediumMercury 2.5 PreviewhighvsGLM 5.3lowBeam 1.0 501B A23BxhighvsGLM 5.1noneClaude Sonnet 5.5mediumvsMercury 2.5 PreviewhighQwen3.6 35B A3BmediumvsBeam 1.0 501B A23BxhighKAT-Coder-Pro V2.5highvsBeam 1.0 501B A23BxhighBeam 1.0 501B A23BxhighvsGrok 4.3mediumMercury 2.5 PreviewhighvsGLM 5.1noneClaude Sonnet 5.5mediumvsBeam 1.0 501B A23BxhighLaguna XS 2.1mediumFree AvailablevsBeam 1.0 501B A23Bxhigh