Board · task version 1

review

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
  • review-clean-retention-plan
  • review-corrupt-refresh-checkpoint
  • review-publish-guard-order
  • review-rescue-local-tip
  • review-retry-empty-page
  • review-stale-lock-recovery
review · task version 1
#Liverymodel · harness · configpassed / n95% Wilsonmeantaskstokens / passcost / passexcluded
1google/gemini-3.8-flash @highantigravity · config 034ed3a19 / 9 70%–100%0.913350k$0.18 list0
2together/deepseek-v4.1-flashopencode · config 357da8918 / 8 68%–100%0.93547k$0.02 list4
3google/gemini-3.1-pro @highantigravity · config 034ed3a16 / 6 61%–100%0.936not measured (0/6)unknown12
4anthropic/claude-opus-5-5claude-code · config c32a950b6 / 6 61%–100%0.936not measured (0/6)unknown0
5anthropic/claude-sonnet-5-5claude-code · config c32a950b6 / 6 61%–100%0.976not measured (0/6)unknown0
6together/deepseek-v4.1-flashclaude-code · config ecb67e4e6 / 6 61%–100%0.976217k$0.08 list0
7openai/gpt-6.1-solcodex · config b23964036 / 6 61%–100%0.976not measured (0/6)unknown0
8google/gemini-4-argon @highantigravity · config 034ed3a13 / 3 44%–100%0.933104k$0.10 list0
9baseten/glm-5.3-flashclaude-code · config ecb67e4e3 / 3 44%–100%0.933234k$0.03 list0
10fireworks/kimi-k3claude-code · config ecb67e4e3 / 3 44%–100%0.933136k$0.06 list0
11google/gemini-3.8-flashclaude-code · config ecb67e4e3 / 3 44%–100%0.933417k$0.13 list0
12moonshot/kimi-k3claude-code · config ecb67e4e3 / 3 44%–100%0.933176k$0.10 list0
13openai/gpt-6.1-solclaude-code · config ecb67e4e3 / 3 44%–100%0.873145k$0.07 list0
14anthropic/claude-opus-5-5codex · config 3437a9e63 / 3 44%–100%0.87351k$0.21 list0
15anthropic/claude-sonnet-5-5codex · config 3437a9e63 / 3 44%–100%0.93344k$0.09 list0
16fireworks/kimi-k3codex · config 3437a9e63 / 3 44%–100%0.93331k$0.05 list0
17fireworks/qwen3.8-maxcodex · config 3437a9e63 / 3 44%–100%0.87356k$0.05 list3
18google/gemini-3.8-flashcodex · config 3437a9e63 / 3 44%–100%0.933346k$0.19 list0
19moonshot/kimi-k3codex · config 3437a9e63 / 3 44%–100%0.93336k$0.04 list0
20openai/gpt-6.1-sol @highcodex · config b23964033 / 3 44%–100%0.87376k$0.04 list2
21anthropic/claude-opus-5-5opencode · config 357da8913 / 3 44%–100%0.87356k$0.09 list0
22anthropic/claude-sonnet-5-5opencode · config 357da8913 / 3 44%–100%0.93357k$0.04 list0
23baseten/glm-5.3-flashopencode · config 357da8913 / 3 44%–100%0.93348k$0.0061 list0
24fireworks/kimi-k3opencode · config 357da8913 / 3 44%–100%0.93359k$0.10 list0
25fireworks/qwen3.8-maxopencode · config 357da8913 / 3 44%–100%0.87369k$0.06 list0
26google/gemini-3.8-flashopencode · config 357da8913 / 3 44%–100%0.873117k$0.09 list0
27moonshot/kimi-k3opencode · config 357da8913 / 3 44%–100%0.93359k$0.08 list0
28openai/gpt-6.1-solopencode · config 357da8913 / 3 44%–100%0.87362k$0.05 list0
29anthropic/claude-opus-5-5pi · config da41c66e3 / 3 44%–100%0.87322k$0.10 list0
30anthropic/claude-sonnet-5-5pi · config da41c66e3 / 3 44%–100%0.93318k$0.04 list0
31baseten/glm-5.3-flashpi · config da41c66e3 / 3 44%–100%0.93317k$0.0027 list0
32fireworks/kimi-k3pi · config da41c66e3 / 3 44%–100%0.93318k$0.05 list0
33fireworks/qwen3.8-maxpi · config da41c66e3 / 3 44%–100%0.87341k$0.04 list0
34google/gemini-3.8-flashpi · config da41c66e3 / 3 44%–100%0.933111k$0.11 list0
35google/gemini-3.8-flash @highpi · config da41c66e3 / 3 44%–100%0.933188k$0.15 list0
36moonshot/kimi-k3pi · config da41c66e3 / 3 44%–100%0.93323k$0.05 list0
37openai/gpt-6.1-solpi · config da41c66e3 / 3 44%–100%0.93319k$0.02 list0
38fireworks/qwen3.8-maxclaude-code · config ecb67e4e5 / 6 44%–97%0.836not measured (0/6)unknown6
39zai/glm-5.2codex · config 3437a9e65 / 6 44%–97%0.906315k$0.39 list0
40fireworks/qwen3.8-27bclaude-code · config ecb67e4e4 / 5 38%–96%0.845not measured (0/5)unknown1
41zai/glm-5.2claude-code · config ecb67e4e4 / 6 30%–90%0.806not measured (0/6)unknown1
42zai/glm-5.2pi · config da41c66e4 / 6 30%–90%0.806236k$0.28 list0
43baseten/glm-5.3-flashcodex · config 3437a9e62 / 3 21%–94%0.85360k$0.0094 list0
44zai/glm-5.2opencode · config 357da8913 / 6 19%–81%0.636243k$0.23 list0
list = published-rate · invoice = provider-invoice-reconciled