- Rank
- #232
- Total Output Tokens
- 96,943
- Response Time (avg)
- 4.40s
- Total Cost
- $0.121
Mercury 2 (medium) vs Grok 4.7 (high)
Grok 4.7 (high) leads on average score with 6.7 vs 6.6. Mercury 2 (medium) has the lower benchmark cost at $0.121 vs $3.037. Mercury 2 (medium) is faster at 4.40s vs 122.19s, with pass rates of 53.6% vs 72.5%.
Compared models
- Rank
- #221
- Total Output Tokens
- 487,184
- Response Time (avg)
- 122.19s
- Total Cost
- $3.037
Recommended model
Mercury 2 (medium)
Its score stays close to the best score here (6.6 vs 6.7), while costing about 25.3x less than Grok 4.7 (high).
Detailed comparison
| Metric | Mercury 2 Mercury 2 medium | Grok 4.7 Grok 4.7 high |
|---|---|---|
| Score | 6.6 | 6.7 |
| Rank | #232 | #221 |
| Reliability | 10.0 | 9.6 |
| Consistency | 8.1 | 7.7 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 53.6% | 72.5% |
| Flaky tests | 5 | 7 |
| Total Runs | 69 | 69 |
| Cost per result | 1.201 | 23.360 |
| Total Cost | $0.121 | $3.037 |
| Input Price | $0.250 / 1M | $2.000 / 1M |
| Output Price | $0.750 / 1M | $6.000 / 1M |
| Cache Read Price | $0.025 / 1M | $0.500 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 189,300 | 329,276 |
| Output Tokens | 10,854 | 8,172 |
| Reasoning Tokens | 86,089 | 479,012 |
| Response Time (avg) | 4.40s | 122.19s |
| Response Time (max) | 34.92s | 573.57s |
| Response Time (total) | 96.81s | 2810.40s |
| Parameters | ~100B | ~1.7T total (~170B 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.
#232 Mercury 2
medium- Cost
- $0.002
- Time
- 2.1s
- Tokens
- 1,702 tok
#221 SpaceXAI: Grok 4.7
high- Cost
- $0.110
- Time
- 301.3s
- Tokens
- 23,143 tok
Category Breakdown
Quick Compare
Switch Comparison Pair
MiniMax M3mediumvsGrok 4.7highEmber-1maxvsGrok 4.7highGPT 5.3 ChatdefaultvsGrok 4.7highMercury 2mediumvsStep 3.7 FlashhighGPT-5.6 SolnonevsGrok 4.7highSolar Pro 4lowvsGrok 4.7highQwen3.5-FlashnonevsGrok 4.7highMercury 2mediumvsLongCat 2.0lowMercury 2mediumvsKAT-Coder-Pro V2.5lowGrok 4.7highvsGLM 5.3 FlashlowGPT-5.5nonevsGrok 4.7highGrok 4.7highvsGLM 5.2none