We tested DeepSeek V4 Flash against Kimi K3 and GLM 5.2 on 30 challenging agentic tasks.
DeepSeek was 2.5x faster than GLM and 1.4x faster than Kimi at a similar success rate, despite using the most tokens per task. 🧵🧵🧵
Hermes and Pi Agent led on the average cost per task, while Claude Code cost about 3.7x as much as Pi:
- $0.39 Hermes Agent
- $0.40 Pi Agent
- $0.47 Codex
- $0.51 OpenCode
- $0.54 Kimi Code
- $1.47 Claude Code
The median cost tells the same story: $0.29 in Pi Agent and Hermes, $0.35 in OpenCode, $0.38 in Kimi Code, $0.39 in Codex and $0.72 in Claude Code, so the cost gap holds for a typical task and is not driven by a few expensive runs.
We calculated these costs using Kimi K3’s list prices: $3/1M input tokens, $0.30/1M cached input tokens, and $15/1M output tokens.
Lesson: If you want to reduce agent costs, examine the harness before switching models. In our data, the harness changed the cost by 9× while the model’s capabilities remained about the same.
As we mentioned, success rates stayed close, but speed and token efficiency split between harnesses:
- Success rate: 22/28 for Kimi Code, 21/28 for Hermes, 20/28 for Claude Code
- Median time per task: 179s in Hermes, 297s in Kimi Code, 348s in Claude Code
So the fastest harness (Hermes) and the most token-efficient one (Kimi Code) were different.
The median task consumed nearly 6x more tokens in Claude Code than in Kimi Code:
- 61k in Kimi Code
- 67k in Hermes
- 340k in Claude Code
At K3's $3/M input rate (input tokens make up roughly 95% of agentic workloads), the average cost per task was:
- $0.22 in Kimi Code
- $0.28 in Hermes
- $2.00 in Claude Code
We ran Kimi K3 through 3 agent harnesses (Claude Code, Hermes, Kimi Code) on 28 identical tasks.
All 3 harnesses completed the tasks at similar success rates, but the interesting story is token efficiency: the same task cost up to 30x more tokens depending on the harness. 🧵🧵