Muse Ember (max) vs Inkling 2 Mini (local Q4) (minimal)
The average score is effectively tied at 8.6 vs 8.7. Inkling 2 Mini (local Q4) (minimal) has the lower benchmark cost at ~$0.206 vs $0.346. Muse Ember (max) is faster at 19.05s vs 108.28s, with pass rates of 72.5% vs 73.9%.
Last updated at:
2026-11-22
Compared models
Rank
#112
Total Output Tokens
637,819
Response Time (avg)
19.05s
Total Cost
$0.346
Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
Rank
#108
Total Output Tokens
219,084
Response Time (avg)
108.28s
Total Cost
~$0.206Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 2.0753 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.205185.
Recommended modelMuse Ember (max)
It has the best score here (8.6), while responding about 5.7x faster than Inkling 2 Mini (local Q4) (minimal).
Inkling 2 Mini (local Q4)Inkling 2 Mini (local Q4)minimalCandidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.Release: 2026-11-20
Inkling 2 Mini (local Q4)Inkling 2 Mini (local Q4)minimalCandidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.Release: 2026-11-20
Score
8.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#112
#108
Reliability
10.0First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
9.8First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
A test is fully passed only if every run passed for that test.Wrong answer: 4Did not follow instructions: 1Invalid tool call: 1Response Time (avg)108.28sResponse Time (max)1322.88sResponse Time (total)2490.37sA test is fully passed only if every run passed for that test.…
Attempt pass rate
72.5%Attempt pass rate = passed attempts / total attempts across runs.…
73.9%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
69Total Runs…
69Total Runs…
Cost per result
2.304
~1.207Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 2.0753 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.205185.
Total Cost
$0.346
~$0.206Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 2.0753 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.205185.
Input Price
$0.100 / 1MInput Price…
N/AInput Price…
Output Price
$0.500 / 1MOutput Price…
N/AOutput Price…
Cache Read Price
$0.004 / 1MCache Read Price…
N/ACache Read Price…
Cache Write Price
$0.125 / 1MCache Write Price…
N/ACache Write Price…
Total Input Tokens
265,489Total Input Tokens…
309,808Total Input Tokens…
Output Tokens
12,179Output Tokens…
1,579Output Tokens…
Reasoning Tokens
625,640Reasoning Tokens…
217,505Reasoning Tokens…
Response Time (avg)
19.05sResponse Time (avg)…
108.28sResponse Time (avg)…
Response Time (max)
79.28sResponse Time (max)…
1322.88sResponse Time (max)…
Response Time (total)
438.15sResponse Time (total)…
2490.37sResponse Time (total)…
Parameters
~150B total (~10B active)
26.4B total (3.4B 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.
#112 Muse Ember
max
Cost
$0.008
Time
23.3s
Tokens
14,138 tok
#108 Thinking Machines: Inkling 2 Mini (local Q4)
minimalCandidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
Cost
~$0.002Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0188 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.001862.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)44.84sResponse Time (max)44.84sResponse Time (total)44.84sA test is fully passed only if every run passed for that test.…
44.84sResponse Time (avg)…
151,338Total Input Tokens…
2,634Output Tokens…
2,485Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)59.04sResponse Time (max)59.04sResponse Time (total)59.04sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.20sResponse Time (max)5.23sResponse Time (total)12.79sA test is fully passed only if every run passed for that test.…
3.20sResponse Time (avg)…
798Total Input Tokens…
346Output Tokens…
7,685Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.20sResponse Time (max)10.50sResponse Time (total)24.78sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)12.46sResponse Time (max)15.19sResponse Time (total)37.37sA test is fully passed only if every run passed for that test.…
12.46sResponse Time (avg)…
7,410Total Input Tokens…
1,595Output Tokens…
49,511Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)225.36sResponse Time (max)477.83sResponse Time (total)676.09sA test is fully passed only if every run passed for that test.…
7.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
83.3%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)20.27sResponse Time (max)32.51sResponse Time (total)40.54sA test is fully passed only if every run passed for that test.…
20.27sResponse Time (avg)…
83,504Total Input Tokens…
3,565Output Tokens…
86,235Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
6.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
50.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)671.08sResponse Time (max)1322.88sResponse Time (total)1342.15sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.07sResponse Time (max)6.95sResponse Time (total)10.14sA test is fully passed only if every run passed for that test.…
5.07sResponse Time (avg)…
7,215Total Input Tokens…
414Output Tokens…
7,961Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)28.12sResponse Time (max)35.26sResponse Time (total)56.25sA test is fully passed only if every run passed for that test.…
3.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 2No answer: 1Response Time (avg)54.31sResponse Time (max)79.28sResponse Time (total)162.92sA test is fully passed only if every run passed for that test.…
54.31sResponse Time (avg)…
873Total Input Tokens…
1,694Output Tokens…
226,070Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
7.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
66.7%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)88.16sResponse Time (max)147.25sResponse Time (total)264.48sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.35sResponse Time (max)3.35sResponse Time (total)3.35sA test is fully passed only if every run passed for that test.…
3.35sResponse Time (avg)…
522Total Input Tokens…
149Output Tokens…
2,454Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
5.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)6.44sResponse Time (max)6.44sResponse Time (total)6.44sA test is fully passed only if every run passed for that test.…
6.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
50.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)3.85sResponse Time (max)5.90sResponse Time (total)7.69sA test is fully passed only if every run passed for that test.…
3.85sResponse Time (avg)…
759Total Input Tokens…
222Output Tokens…
7,257Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
9.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.25sResponse Time (max)5.70sResponse Time (total)10.49sA test is fully passed only if every run passed for that test.…
5.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)29.41sResponse Time (max)78.68sResponse Time (total)88.23sA test is fully passed only if every run passed for that test.…
29.41sResponse Time (avg)…
786Total Input Tokens…
890Output Tokens…
203,560Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
6.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Wrong answer: 1Response Time (avg)7.32sResponse Time (max)7.68sResponse Time (total)21.96sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.57sResponse Time (max)4.57sResponse Time (total)4.57sA test is fully passed only if every run passed for that test.…
4.57sResponse Time (avg)…
12,056Total Input Tokens…
448Output Tokens…
1,402Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.52sResponse Time (max)7.52sResponse Time (total)7.52sA test is fully passed only if every run passed for that test.…
3.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)25.72sResponse Time (max)25.72sResponse Time (total)25.72sA test is fully passed only if every run passed for that test.…
25.72sResponse Time (avg)…
228Total Input Tokens…
222Output Tokens…
31,020Reasoning Tokens…
Inkling 2 Mini (local Q4)Candidate responses were generated on local hardware. OpenRouter was used only for judging. inkling-2-mini-ud-q4_k_xl · UD-Q4_K_XL · llama.cpp b12631-e300919cc · NVIDIA GeForce RTX 3090.
3.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)21.18sResponse Time (max)21.18sResponse Time (total)21.18sA test is fully passed only if every run passed for that test.…