- Rank
- #128
- Total Output Tokens
- 298,893
- Response Time (avg)
- 29.10s
- Total Cost
- $0.402
Inkling Small (high) vs Grok 4.7 (medium)
Inkling Small (high) leads on average score with 7.4 vs 7.3. Inkling Small (high) has the lower benchmark cost at $0.402 vs $3.501. Inkling Small (high) is faster at 29.10s vs 117.65s, with pass rates of 66.7% vs 78.3%.
Compared models
- Rank
- #134
- Total Output Tokens
- 474,745
- Response Time (avg)
- 117.65s
- Total Cost
- $3.501
Recommended model
Inkling Small (high)
It has the best score here (7.4), while costing about 8.7x less than Grok 4.7 (medium).
Detailed comparison
| Metric | Inkling Small Inkling Small high Free Available | Grok 4.7 Grok 4.7 medium |
|---|---|---|
| Score | 7.4 | 7.3 |
| Rank | #128 | #134 |
| Reliability | 10.0 | 9.8 |
| Consistency | 9.3 | 8.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 66.7% | 78.3% |
| Flaky tests | 2 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 2.868 | 19.582 |
| Total Cost | $0.402 | $3.501 |
| Input Price | $0.450 / 1M | $2.000 / 1M |
| Output Price | $1.200 / 1M | $6.000 / 1M |
| Total Input Tokens | 85,669 | 326,066 |
| Output Tokens | 6,092 | 5,726 |
| Reasoning Tokens | 292,801 | 469,019 |
| Response Time (avg) | 29.10s | 117.65s |
| Response Time (max) | 122.60s | 660.89s |
| Response Time (total) | 669.40s | 2706.03s |
| Parameters | 276B total (12B active) | ~1.7T total (~170B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#128 Thinking Machines: Inkling Small
high- Cost
- $0.006
- Time
- 34.7s
- Tokens
- 4,735 tok
#134 SpaceXAI: Grok 4.7
medium- Cost
- $0.047
- Time
- 132.3s
- Tokens
- 9,954 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 23ms | 0 | 0 | 0 | |
| Grok 4.7 | 3.9 | 9.6 | 0.0% | 0 | 372.09s | 218,873 | 1,065 | 39,947 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 6.30s | 702 | 335 | 9,678 | |
| Grok 4.7 | 10.0 | 10.0 | 100.0% | 0 | 16.01s | 2,991 | 54 | 7,224 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 93.23s | 7,374 | 463 | 120,474 | |
| Grok 4.7 | 6.6 | 4.6 | 77.8% | 2 | 312.17s | 10,266 | 349 | 172,347 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 9.9 | 10.0 | 100.0% | 0 | 40.41s | 61,630 | 4,001 | 28,812 | |
| Grok 4.7 | 10.0 | 10.0 | 100.0% | 0 | 96.50s | 67,788 | 3,524 | 38,447 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 3.99s | 7,068 | 216 | 2,763 | |
| Grok 4.7 | 10.0 | 10.0 | 100.0% | 0 | 5.16s | 8,937 | 225 | 2,344 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 5.3 | 10.0 | 33.3% | 0 | 56.28s | 804 | 69 | 84,578 | |
| Grok 4.7 | 5.3 | 7.2 | 44.4% | 1 | 300.37s | 2,523 | 15 | 169,756 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 5.3 | 10.0 | 0.0% | 0 | 3.62s | 501 | 153 | 1,395 | |
| Grok 4.7 | 5.4 | 2.5 | 66.7% | 1 | 32.39s | 1,077 | 76 | 5,830 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 9.8 | 10.0 | 100.0% | 0 | 3.94s | 708 | 94 | 2,742 | |
| Grok 4.7 | 8.4 | 6.9 | 83.3% | 1 | 6.68s | 1,857 | 57 | 2,742 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 4.8 | 4.4 | 44.5% | 2 | 14.39s | 714 | 482 | 18,286 | |
| Grok 4.7 | 10.0 | 10.0 | 100.0% | 0 | 18.46s | 2,430 | 135 | 9,678 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 2.91s | 5,949 | 249 | 577 | |
| Grok 4.7 | 10.0 | 10.0 | 100.0% | 0 | 4.79s | 8,535 | 206 | 406 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 49.27s | 219 | 30 | 23,496 | |
| Grok 4.7 | 3.0 | 10.0 | 0.0% | 0 | 123.05s | 789 | 20 | 20,298 |
Quick Compare
Switch Comparison Pair
Inkling SmallhighFree AvailablevsGrok 4.7lowLongCat 2.0highvsGrok 4.7mediumSeed-2.0-CodemediumvsInkling SmallhighFree AvailableDeepSeek V4 Pro 0423nonevsInkling SmallhighFree AvailableDeepSeek V4 Flash 0731lowvsInkling SmallhighFree AvailableGrok 4.7mediumvsGLM 5.3 FlashhighQwen3.6 FlashmediumvsInkling SmallhighFree AvailableGPT-5.6 LunamediumvsInkling SmallhighFree AvailableGemma 4 26B A4BmediumFree AvailablevsInkling SmallhighFree AvailableQwen3.5-27BnonevsGrok 4.7mediumGemini 3.8 FlashlowvsGrok 4.7mediumDeepSeek V4 Pro 0423nonevsGrok 4.7medium