Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Qwen3.5-122B-A10B
63
Sakana Fugu Ultra
100
Verified leaderboard positions: Qwen3.5-122B-A10B #14 · Sakana Fugu Ultra unranked
Pick Sakana Fugu Ultra if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if you want the cheaper token bill.
Agentic
+26.0 difference
Coding
+11.5 difference
Knowledge
+13.9 difference
Qwen3.5-122B-A10B
Sakana Fugu Ultra
$0 / $0
$5 / $30
N/A
N/A
N/A
N/A
262K
1M
Pick Sakana Fugu Ultra if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if you want the cheaper token bill.
Sakana Fugu Ultra is clearly ahead on the provisional aggregate, 100 to 63. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Sakana Fugu Ultra's sharpest advantage is in agentic, where it averages 82.1 against 56.1. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 49.4% to 82.1%.
Sakana Fugu Ultra is also the more expensive model on tokens at $5.00 input / $30.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Sakana Fugu Ultra gives you the larger context window at 1M, compared with 262K for Qwen3.5-122B-A10B.
Sakana Fugu Ultra is ahead on BenchLM's provisional leaderboard, 100 to 63. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 49.4% and 82.1%.
Sakana Fugu Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 81.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Sakana Fugu Ultra has the edge for coding in this comparison, averaging 83.5 versus 72. Qwen3.5-122B-A10B stays close enough that the answer can still flip depending on your workload.
Sakana Fugu Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 56.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.