Board · task version 2

docs

Each board ranks harness × model combinations on one suite by pass rate with a 95% Wilson interval; rows are not comparable across suites or task versions.

6 tasks
  • docs-cache-config
  • docs-config-loader-keys
  • docs-gym-baseline-keys
  • docs-gym-run-flags
  • docs-retry-behavior-diff
  • docs-snapshot-new-command
docs · task version 2
#Liverymodel · harness · configpassed / n95% Wilsonmeantaskstokens / passcost / passexcluded
1moonshot/kimi-k3claude-code · config ecb67e4e6 / 6 61%–100%1.006205k$0.14 list3
2anthropic/claude-opus-5-5codex · config 3437a9e66 / 6 61%–100%1.00645k$0.20 list0
3anthropic/claude-sonnet-5-5codex · config 3437a9e66 / 6 61%–100%1.00636k$0.08 list0
4fireworks/kimi-k3codex · config 3437a9e66 / 6 61%–100%1.00643k$0.06 list0
5moonshot/kimi-k3codex · config 3437a9e66 / 6 61%–100%1.00655k$0.06 list0
6openai/gpt-6.1-sol @highcodex · config b23964036 / 6 61%–100%1.00686k$0.04 list0
7moonshot/kimi-k3opencode · config 357da8916 / 6 61%–100%1.00676k$0.10 list0
8anthropic/claude-opus-5-5pi · config da41c66e6 / 6 61%–100%1.00621k$0.11 list0
9baseten/glm-5.3-flashpi · config da41c66e6 / 6 61%–100%1.00623k$0.0037 list0
10fireworks/kimi-k3pi · config da41c66e6 / 6 61%–100%1.00636k$0.08 list0
11fireworks/qwen3.8-maxpi · config da41c66e6 / 6 61%–100%1.00666k$0.06 list0
12google/gemini-4-argon @highantigravity · config 034ed3a13 / 3 44%–100%1.003160k$0.17 list0
13anthropic/claude-opus-5-5claude-code · config c32a950b3 / 3 44%–100%1.0031.06M$0.36 list0
14anthropic/claude-sonnet-5-5claude-code · config c32a950b3 / 3 44%–100%1.003904k$0.15 list0
15google/gemini-3.8-flash @highclaude-code · config ecb67e4e3 / 3 44%–100%1.003626k$0.19 list0
16google/gemini-3.8-flash @lowclaude-code · config ecb67e4e3 / 3 44%–100%1.003186k$0.13 list0
17google/gemini-3.8-flash @mediumclaude-code · config ecb67e4e3 / 3 44%–100%1.003204k$0.14 list0
18google/gemini-3.8-flash @lowcodex · config 3437a9e63 / 3 44%–100%1.003168k$0.11 list0
19openai/gpt-6.1-sol @mediumcodex · config b23964033 / 3 44%–100%1.00388k$0.04 list0
20google/gemini-3.8-flash @highopencode · config 357da8913 / 3 44%–100%1.003454k$0.20 list0
21google/gemini-3.8-flash @highpi · config da41c66e3 / 3 44%–100%1.003359k$0.22 list0
22google/gemini-3.8-flash @lowpi · config da41c66e3 / 3 44%–100%1.00352k$0.04 list0
23google/gemini-3.8-flash @highantigravity · config 034ed3a15 / 6 44%–97%0.836436k$0.22 list0
24fireworks/kimi-k3claude-code · config ecb67e4e5 / 6 44%–97%0.986207k$0.16 list0
25google/gemini-3.8-flashclaude-code · config ecb67e4e5 / 6 44%–97%0.986591k$0.16 list0
26together/deepseek-v4.1-flashclaude-code · config ecb67e4e5 / 6 44%–97%0.986317k$0.10 list4
27zai/glm-5.2claude-code · config ecb67e4e5 / 6 44%–97%0.986241k$0.11 list0
28baseten/glm-5.3-flashcodex · config 3437a9e65 / 6 44%–97%0.83665k$0.0095 list0
29fireworks/qwen3.8-maxcodex · config 3437a9e65 / 6 44%–97%0.836107k$0.09 list0
30google/gemini-3.8-flashcodex · config 3437a9e65 / 6 44%–97%0.986240k$0.16 list0
31together/deepseek-v4.1-flashcodex · config 3437a9e65 / 6 44%–97%0.83673k$0.02 list0
32baseten/glm-5.3-flashopencode · config 357da8915 / 6 44%–97%0.98675k$0.01 list0
33fireworks/kimi-k3opencode · config 357da8915 / 6 44%–97%0.83695k$0.15 list0
34fireworks/qwen3.8-maxopencode · config 357da8915 / 6 44%–97%0.836103k$0.09 list0
35google/gemini-3.8-flashopencode · config 357da8915 / 6 44%–97%0.836229k$0.16 list0
36together/deepseek-v4.1-flashopencode · config 357da8915 / 6 44%–97%0.96663k$0.02 list0
37zai/glm-5.2opencode · config 357da8915 / 6 44%–97%0.98691k$0.06 list0
38anthropic/claude-sonnet-5-5pi · config da41c66e5 / 6 44%–97%0.98626k$0.06 list0
39openai/gpt-6.1-solpi · config da41c66e5 / 6 44%–97%0.97629k$0.03 list0
40together/deepseek-v4.1-flashpi · config da41c66e5 / 6 44%–97%0.98635k$0.01 list0
41zai/glm-5.2pi · config da41c66e5 / 6 44%–97%0.98660k$0.06 list0
42fireworks/qwen3.8-maxclaude-code · config ecb67e4e4 / 6 30%–90%0.976363k$0.20 list0
43zai/glm-5.2codex · config 3437a9e64 / 6 30%–90%0.976116k$0.10 list0
44openai/gpt-6.1-solcodex · config b23964034 / 6 30%–90%0.976121k$0.05 list0
45anthropic/claude-sonnet-5-5opencode · config 357da8914 / 6 30%–90%0.97687k$0.08 list0
46openai/gpt-6.1-solopencode · config 357da8914 / 6 30%–90%0.966125k$0.09 list0
47google/gemini-3.8-flashpi · config da41c66e4 / 6 30%–90%0.676262k$0.17 list0
48moonshot/kimi-k3pi · config da41c66e4 / 6 30%–90%0.95652k$0.10 list0
49openai/gpt-6.1-solclaude-code · config ecb67e4e2 / 3 21%–94%0.973247k$0.12 list0
50google/gemini-3.8-flash @highcodex · config 3437a9e62 / 3 21%–94%0.973652k$0.38 list0
51google/gemini-3.8-flash @lowopencode · config 357da8912 / 3 21%–94%0.973166k$0.11 list0
52baseten/glm-5.3-flashclaude-code · config ecb67e4e3 / 6 19%–81%0.956461k$0.06 list6
53anthropic/claude-opus-5-5opencode · config 357da8912 / 6 10%–70%0.946170k$0.34 list0
54google/gemini-3.1-pro @highantigravity · config 034ed3a10 / 3 0%–56%1no passesunknown0
list = published-rate · invoice = provider-invoice-reconciled