Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Kimi K2.6
80
Sakana Fugu Ultra
100
Verified leaderboard positions: Kimi K2.6 #13 · Sakana Fugu Ultra unranked
Pick Sakana Fugu Ultra if you want the stronger benchmark profile. Kimi K2.6 only becomes the better choice if you want the cheaper token bill.
Agentic
+9.0 difference
Coding
+11.5 difference
Knowledge
+41.7 difference
Kimi K2.6
Sakana Fugu Ultra
$0.95 / $4
$5 / $30
N/A
N/A
N/A
N/A
256K
1M
Pick Sakana Fugu Ultra if you want the stronger benchmark profile. Kimi K2.6 only becomes the better choice if you want the cheaper token bill.
Sakana Fugu Ultra is clearly ahead on the provisional aggregate, 100 to 80. 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 knowledge, where it averages 95.5 against 53.8. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 66.7% 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 $0.95 input / $4.00 output per 1M tokens for Kimi K2.6. That is roughly 7.5x on output cost alone. Sakana Fugu Ultra gives you the larger context window at 1M, compared with 256K for Kimi K2.6.
Sakana Fugu Ultra is ahead on BenchLM's provisional leaderboard, 100 to 80. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 66.7% and 82.1%.
Sakana Fugu Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 53.8. 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. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Sakana Fugu Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 73.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Estimates at 50,000 req/day · 1000 tokens/req average.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.