Understand this story
On August 26, 2026, Fireworks AI released evaluation results for DeepSeek V4 Pro 0813 and announced that training support for the model is now live on Fireworks, supporting SFT, DPO, and RFT. The evaluation used four benchmark suites: SWE-Bench Verified, LiveCodeBench v6, Aider Polyglot, and Terminal-Bench 2.1. Fireworks stated that DeepSeek V4 Pro scored 95.2% on SWE-Bench Verified, higher than Kimi K3's 92.6% and Fable 5's 85.4%; on LiveCodeBench v6 it scored 92.0%. In terms of cost, the model spent $0.309 per task solved on SWE-Bench, compared with $0.808 for Fable 5; on LiveCodeBench the figures were $0.040 and $0.225, respectively. On a combined sample of 409 tasks, the oracle routing accuracy of DeepSeek V4 Pro and Fable 5 was 92.4%, higher than the 86.6% achieved by Fable 5 alone, with a per-task cost
AI-generated from public reports
Latest development · Report
Fireworks Evaluates DeepSeek V4 Pro Against Fable 5 and Kimi K3Developments
1 confirmed developments
- Source:Fireworks AI
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Aug 26
Fireworks AIFirst-party
Fireworks Evaluates DeepSeek V4 Pro Against Fable 5 and Kimi K3
Fireworks tested DeepSeek V4 Pro 0813 on four benchmarks: SWE-Bench Verified, LiveCodeBench v6, Aider Polyglot, and Terminal-Bench 2.1. It scored 95.2% on SWE-Bench Verified, higher than Kimi K3's 92.6% and Fable 5's 85.4%, and 92.0% on LiveCodeBench v6. On cost, DeepSeek V4 Pro spent $0.309 per task solved on SWE-bench, versus $0.808 for Fable 5; on LiveCodeBench the figures were $0.040 and $0.225, respectively. Its weakness is the multilingual breadth of Aider Polyglot, where it scored only 48.9% on Java, versus 74.5% for Fable 5. After oracle routing on a combined set of 409 tasks, accuracy was 92.4%, higher than the 86.6% achieved by Fable 5 alone, at a cost of $0.279 versus $4.510 per task, with 86.3% of tasks routed to V4 Pro.
fireworks_aiFirst-partySelected
English translation is being prepared.