Fireworks benchmarks Kimi K3 vs Fable 5: routing the two hits 93% accuracy at far lower cost

Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

Fireworks ran ~1,030 real agent tasks comparing Kimi K3 and Fable 5. Head-to-head on SWE: K3 92.4%, Fable 92.6% — a near tie. Under the hood, K3 excels at symbolic math and dev tooling; Fable wins on web and data viz. Routing between the two lifts accuracy to 93% and cuts cost up to 50x on long agent loops. Oracle routing shows K3 can handle 72–96% of tasks, but a practical router still needs an order of magnitude more routing data.

Why it matters: Fireworks ran ~1,030 real agent tasks comparing K3 and Fable, with concrete numbers and a task-type breakdown. The finding that routing between the two beats either alone is useful and testable. Score stays at 78 rather than higher because this is a single-source vendor post—F...