- 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 (medium)
Beam 1.0 501B A23B (medium) leads on average score with 6.6 vs 6.5. Mercury 2.5 Preview (high) has the lower benchmark cost at $0.040 vs $0.499. Beam 1.0 501B A23B (medium) is faster at 6.27s vs 7.61s, with pass rates of 65.2% vs 65.2%.
Compared models
- Rank
- #220
- Total Output Tokens
- 98,521
- Response Time (avg)
- 6.27s
- Total Cost
- $0.499
Recommended model
Mercury 2.5 Preview (high)
Its score stays close to the best score here (6.5 vs 6.6), while costing about 12.8x less than Beam 1.0 501B A23B (medium).
Detailed comparison
| Metric | Mercury 2.5 Preview Mercury 2.5 Preview high | Beam 1.0 501B A23B Beam 1.0 501B A23B medium |
|---|---|---|
| Score | 6.5 | 6.6 |
| Rank | #224 | #220 |
| Reliability | 9.9 | 10.0 |
| Consistency | 8.0 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 65.2% | 65.2% |
| Flaky tests | 6 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 0.319 | 3.561 |
| Total Cost | $0.040 | $0.499 |
| 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 | 202,937 |
| Output Tokens | 3,178 | 4,328 |
| Reasoning Tokens | 177,419 | 94,193 |
| Response Time (avg) | 7.61s | 6.27s |
| Response Time (max) | 86.84s | 31.55s |
| Response Time (total) | 175.08s | 144.28s |
| 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
#220 Beam 1.0 501B A23B
medium- Cost
- $0.005
- Time
- 11.8s
- Tokens
- 4,267 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 | 31.55s | 172,837 | 2,588 | 9,026 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 1.62s | 1,113 | 232 | 4,706 |
| 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 | 11.81s | 7,791 | 440 | 27,204 |
| 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 | 2.62s | 7,665 | 132 | 2,087 |
| 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 | 1.24s | 7,993 | 279 | 1,614 |
| 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 | 2.9 | 7.2 | 11.1% | 1 | 11.66s | 1,113 | 71 | 29,077 |
| 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 | 4.7 | 1.6 | 66.7% | 1 | 1.87s | 615 | 96 | 1,532 |
| 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 | 1.24s | 918 | 102 | 1,834 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 3.91s | 1,029 | 281 | 9,130 |
| 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 | 1.95s | 1,530 | 72 | 440 |
| 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 | 10.13s | 333 | 35 | 7,543 |
Quick Compare
Switch Comparison Pair
KAT-Coder-Pro V2.5lowvsBeam 1.0 501B A23BmediumBeam 1.0 501B A23BmediumvsStep 3.7 FlashhighMercury 2.5 PreviewhighvsQwen3.6 35B A3BmediumMercury 2.5 PreviewhighvsBeam 1.0 501B A23BxhighMercury 2.5 PreviewhighvsGLM 5.3lowClaude Sonnet 5.5mediumvsMercury 2.5 PreviewhighMercury 2.5 PreviewhighvsGLM 5.1noneLongCat 2.0lowvsBeam 1.0 501B A23BmediumMercury 2.5 PreviewhighvsGrok 4.3mediumMercury 2.5 PreviewhighvsLaguna XS 2.1mediumFree AvailableMercury 2.5 PreviewhighvsKAT-Coder-Pro V2.5lowMercury 2.5 PreviewhighvsQwen3.5-122B-A10Bnone