Board · task version 3

hard-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.

1 tasks
  • hard-review-multi-defect-tool-calls
hard-review · task version 3
#Liverymodel · harness · configpassed / n95% Wilsonmeantaskstokens / passcost / passexcluded
1openai/gpt-6.1-sol @mediumcodex · config b239640311 / 11 74%–100%0.821134k$0.08 list1
2openai/gpt-6.1-sol @highcodex · config b239640310 / 10 72%–100%0.841161k$0.10 list1
3anthropic/claude-opus-5-5claude-code · config c32a950b5 / 5 57%–100%1.0011.05M$0.52 list0
4openai/gpt-6.1-solcodex · config b23964035 / 5 57%–100%0.801132k$0.08 list0
5openai/gpt-6.1-sol @xhighcodex · config b23964035 / 5 57%–100%0.921170k$0.12 list0
6google/gemini-3.8-flash @highantigravity · config 034ed3a13 / 3 44%–100%0.801972k$0.50 list0
7together/deepseek-v4.1-flashclaude-code · config ecb67e4e3 / 3 44%–100%0.801337k$0.12 list0
8fireworks/kimi-k3codex · config 3437a9e63 / 3 44%–100%0.80185k$0.15 list0
9zai/glm-5.2codex · config 3437a9e63 / 3 44%–100%0.801552k$0.91 list0
10baseten/glm-5.3-flashopencode · config 357da8913 / 3 44%–100%0.801165k$0.02 list0
11openai/gpt-6.1-solopencode · config 357da8913 / 3 44%–100%0.931190k$0.15 list0
12baseten/glm-5.3-flashpi · config da41c66e3 / 3 44%–100%0.801143k$0.02 list0
13google/gemini-3.1-pro @highantigravity · config 034ed3a12 / 2 34%–100%0.801360kunknown0
14zai/glm-5.2claude-code · config ecb67e4e2 / 2 34%–100%0.801538k$0.59 list1
15together/deepseek-v4.1-flashcodex · config 3437a9e62 / 2 34%–100%0.801117k$0.05 list0
16together/deepseek-v4.1-flashopencode · config 357da8912 / 2 34%–100%0.801156k$0.06 list0
17google/gemini-3.8-flash @mediumantigravity · config 034ed3a11 / 1 21%–100%0.8012.41M$0.66 list0
18google/gemini-4-argon @lowantigravity · config 034ed3a11 / 1 21%–100%0.80185k$0.08 list0
19anthropic/claude-haiku-5-5 @lowclaude-code · config c32a950b1 / 1 21%–100%0.801430k$0.02 list0
20anthropic/claude-haiku-5-5 @mediumclaude-code · config c32a950b1 / 1 21%–100%0.801366k$0.01 list0
21anthropic/claude-opus-5-5 @highclaude-code · config c32a950b1 / 1 21%–100%1.001771k$0.49 list1
22anthropic/claude-opus-5-5 @maxclaude-code · config c32a950b1 / 1 21%–100%1.0014.18M$4.50 list0
23anthropic/claude-opus-5-5 @mediumclaude-code · config c32a950b1 / 1 21%–100%1.0011.26M$0.47 list0
24anthropic/claude-sonnet-5-5claude-code · config c32a950b1 / 1 21%–100%0.8011.04M$0.23 list0
25anthropic/claude-sonnet-5-5 @highclaude-code · config c32a950b1 / 1 21%–100%0.8011.20M$0.25 list0
26anthropic/claude-sonnet-5-5 @lowclaude-code · config c32a950b1 / 1 21%–100%0.801897k$0.18 list0
27anthropic/claude-sonnet-5-5 @maxclaude-code · config c32a950b1 / 1 21%–100%1.0016.26M$3.98 list0
28anthropic/claude-sonnet-5-5 @mediumclaude-code · config c32a950b1 / 1 21%–100%0.801737k$0.15 list0
29fireworks/kimi-k3claude-code · config ecb67e4e1 / 1 21%–100%0.801266k$0.27 list0
30google/gemini-3.8-flash @highclaude-code · config ecb67e4e1 / 1 21%–100%0.8011.43M$0.50 list0
31google/gemini-3.8-flash @lowclaude-code · config ecb67e4e1 / 1 21%–100%0.8014.81M$0.62 list0
32google/gemini-3.8-flash @mediumclaude-code · config ecb67e4e1 / 1 21%–100%0.801835k$0.48 list0
33moonshot/kimi-k3claude-code · config ecb67e4e1 / 1 21%–100%0.801274k$0.22 list0
34openai/gpt-5.6-terra @highclaude-code · config ecb67e4e1 / 1 21%–100%1.001128k$0.11 list0
35openai/gpt-5.6-terra @lowclaude-code · config ecb67e4e1 / 1 21%–100%1.001146k$0.11 list0
36openai/gpt-6-luna @highclaude-code · config ecb67e4e1 / 1 21%–100%1.001153k$0.0063 list0
37openai/gpt-6-luna @maxclaude-code · config ecb67e4e1 / 1 21%–100%1.001133k$0.02 list0
38openai/gpt-6.1-solclaude-code · config ecb67e4e1 / 1 21%–100%0.801259k$0.14 list0
39openai/gpt-6.1-sol @highclaude-code · config ecb67e4e1 / 1 21%–100%0.801176k$0.14 list0
40openai/gpt-6.1-sol @lowclaude-code · config ecb67e4e1 / 1 21%–100%1.001244k$0.10 list1
41openai/gpt-6.1-sol @maxclaude-code · config ecb67e4e1 / 1 21%–100%0.801227k$0.32 list1
42anthropic/claude-haiku-5-5 @highcodex · config 3437a9e61 / 1 21%–100%0.801139k$0.02 list0
43anthropic/claude-haiku-5-5 @lowcodex · config 3437a9e61 / 1 21%–100%0.801133k$0.01 list0
44anthropic/claude-haiku-5-5 @mediumcodex · config 3437a9e61 / 1 21%–100%0.80194k$0.01 list0
45anthropic/claude-haiku-5-5 @xhighcodex · config 3437a9e61 / 1 21%–100%0.801285k$0.04 list0
46anthropic/claude-opus-5-5codex · config 3437a9e61 / 1 21%–100%1.00191k$0.44 list0
47anthropic/claude-opus-5-5 @highcodex · config 3437a9e61 / 1 21%–100%1.001116k$0.54 list0
48anthropic/claude-opus-5-5 @lowcodex · config 3437a9e61 / 1 21%–100%1.001108k$0.46 list0
49anthropic/claude-opus-5-5 @mediumcodex · config 3437a9e61 / 1 21%–100%1.001117k$0.52 list0
50anthropic/claude-opus-5-5 @xhighcodex · config 3437a9e61 / 1 21%–100%1.001246k$1.32 list0
51anthropic/claude-sonnet-5-5 @highcodex · config 3437a9e61 / 1 21%–100%0.80186k$0.19 list1
52anthropic/claude-sonnet-5-5 @mediumcodex · config 3437a9e61 / 1 21%–100%0.80162k$0.14 list0
53anthropic/claude-sonnet-5-5 @xhighcodex · config 3437a9e61 / 1 21%–100%0.801114k$0.31 list0
54fireworks/qwen3.8-maxcodex · config 3437a9e61 / 1 21%–100%0.801204k$0.31 list0
55google/gemini-3.8-flashcodex · config 3437a9e61 / 1 21%–100%0.8011.01M$0.47 list0
56google/gemini-3.8-flash @mediumcodex · config 3437a9e61 / 1 21%–100%0.801591k$0.42 list0
57openai/gpt-5.6-terra @lowcodex · config b23964031 / 1 21%–100%0.801144k$0.08 list0
58openai/gpt-5.6-terra @xhighcodex · config b23964031 / 1 21%–100%0.801255k$0.17 list0
59openai/gpt-6-luna @highcodex · config b23964031 / 1 21%–100%0.801130k$0.0040 list0
60openai/gpt-6-luna @maxcodex · config b23964031 / 1 21%–100%0.801159k$0.0079 list0
61openai/gpt-6-luna @mediumcodex · config b23964031 / 1 21%–100%0.801124k$0.0032 list0
62openai/gpt-6-luna @xhighcodex · config b23964031 / 1 21%–100%0.801202k$0.0096 list0
63openai/gpt-6.1-sol @lowcodex · config b23964031 / 1 21%–100%0.801108k$0.07 list0
64openai/gpt-6.1-sol @maxcodex · config b23964031 / 1 21%–100%1.001255k$0.16 list0
65openai/gpt-6.1-sol @ultracodex · config b23964031 / 1 21%–100%1.001294k$0.16 list0
66anthropic/claude-haiku-5-5 @highopencode · config 357da8911 / 1 21%–100%0.801111k$0.0053 list0
67anthropic/claude-haiku-5-5 @lowopencode · config 357da8911 / 1 21%–100%0.80194k$0.0048 list0
68anthropic/claude-haiku-5-5 @xhighopencode · config 357da8911 / 1 21%–100%0.801243k$0.03 list0
69anthropic/claude-opus-5-5opencode · config 357da8911 / 1 21%–100%1.00179k$0.20 list0
70anthropic/claude-opus-5-5 @highopencode · config 357da8911 / 1 21%–100%1.001142k$0.27 list0
71anthropic/claude-opus-5-5 @mediumopencode · config 357da8911 / 1 21%–100%1.00198k$0.22 list0
72anthropic/claude-opus-5-5 @xhighopencode · config 357da8911 / 1 21%–100%1.001203k$0.54 list3
73anthropic/claude-sonnet-5-5opencode · config 357da8911 / 1 21%–100%0.80190k$0.09 list0
74anthropic/claude-sonnet-5-5 @highopencode · config 357da8911 / 1 21%–100%0.80199k$0.11 list0
75anthropic/claude-sonnet-5-5 @xhighopencode · config 357da8911 / 1 21%–100%0.801140k$0.20 list0
76fireworks/kimi-k3opencode · config 357da8911 / 1 21%–100%0.801107k$0.25 list0
77fireworks/qwen3.8-maxopencode · config 357da8911 / 1 21%–100%0.801139k$0.19 list0
78google/gemini-3.8-flashopencode · config 357da8911 / 1 21%–100%0.801809k$0.41 list0
79google/gemini-3.8-flash @highopencode · config 357da8911 / 1 21%–100%0.801691k$0.48 list0
80google/gemini-3.8-flash @mediumopencode · config 357da8911 / 1 21%–100%0.801587k$0.37 list1
81moonshot/kimi-k3opencode · config 357da8911 / 1 21%–100%0.801140k$0.28 list0
82openai/gpt-5.6-terra @highopencode · config 357da8911 / 1 21%–100%0.801147k$0.12 list0
83openai/gpt-5.6-terra @lowopencode · config 357da8911 / 1 21%–100%1.00154k$0.06 list0
84openai/gpt-6-luna @highopencode · config 357da8911 / 1 21%–100%0.801305k$0.01 list0
85openai/gpt-6-luna @lowopencode · config 357da8911 / 1 21%–100%0.801146k$0.0041 list0
86openai/gpt-6-luna @xhighopencode · config 357da8911 / 1 21%–100%0.801177k$0.01 list0
87openai/gpt-6.1-sol @highopencode · config 357da8911 / 1 21%–100%0.801215k$0.16 list0
88openai/gpt-6.1-sol @lowopencode · config 357da8911 / 1 21%–100%0.80183k$0.06 list0
89openai/gpt-6.1-sol @maxopencode · config 357da8911 / 1 21%–100%0.801316k$0.35 list0
90zai/glm-5.2opencode · config 357da8911 / 1 21%–100%0.801199k$0.19 list0
91anthropic/claude-haiku-5-5 @highpi · config da41c66e1 / 1 21%–100%0.80162k$0.0074 list0
92anthropic/claude-haiku-5-5 @lowpi · config da41c66e1 / 1 21%–100%0.80156k$0.0065 list0
93anthropic/claude-opus-5-5pi · config da41c66e1 / 1 21%–100%1.00158k$0.30 list0
94anthropic/claude-opus-5-5 @highpi · config da41c66e1 / 1 21%–100%1.00153k$0.30 list0
95anthropic/claude-opus-5-5 @lowpi · config da41c66e1 / 1 21%–100%0.80135k$0.16 list0
96anthropic/claude-opus-5-5 @mediumpi · config da41c66e1 / 1 21%–100%1.00160k$0.29 list0
97anthropic/claude-opus-5-5 @xhighpi · config da41c66e1 / 1 21%–100%1.001115k$0.81 list0
98anthropic/claude-sonnet-5-5 @highpi · config da41c66e1 / 1 21%–100%0.80143k$0.11 list0
99anthropic/claude-sonnet-5-5 @mediumpi · config da41c66e1 / 1 21%–100%0.80146k$0.11 list0
100anthropic/claude-sonnet-5-5 @xhighpi · config da41c66e1 / 1 21%–100%0.80155k$0.16 list0
101fireworks/kimi-k3pi · config da41c66e1 / 1 21%–100%0.801121k$0.32 list0
102google/gemini-3.8-flash @highpi · config da41c66e1 / 1 21%–100%0.801782k$0.61 list0
103google/gemini-3.8-flash @mediumpi · config da41c66e1 / 1 21%–100%0.801879k$0.48 list0
104moonshot/kimi-k3pi · config da41c66e1 / 1 21%–100%0.801109k$0.29 list0
105openai/gpt-5.6-terra @lowpi · config da41c66e1 / 1 21%–100%1.00133k$0.05 list0
106openai/gpt-6-luna @highpi · config da41c66e1 / 1 21%–100%1.00143k$0.0034 list0
107openai/gpt-6-luna @maxpi · config da41c66e1 / 1 21%–100%0.801101k$0.01 list0
108openai/gpt-6-luna @xhighpi · config da41c66e1 / 1 21%–100%1.00160k$0.0071 list0
109openai/gpt-6.1-solpi · config da41c66e1 / 1 21%–100%0.80175k$0.09 list0
110openai/gpt-6.1-sol @highpi · config da41c66e1 / 1 21%–100%1.00166k$0.07 list0
111openai/gpt-6.1-sol @lowpi · config da41c66e1 / 1 21%–100%1.00143k$0.04 list0
112openai/gpt-6.1-sol @maxpi · config da41c66e1 / 1 21%–100%1.00185k$0.16 list0
113anthropic/claude-opus-5-5 @xhighclaude-code · config c32a950b4 / 5 38%–96%0.9211.78M$1.27 list1
114together/deepseek-v4.1-flashpi · config da41c66e4 / 5 38%–96%0.761198k$0.08 list0
115fireworks/qwen3.8-maxclaude-code · config ecb67e4e3 / 4 30%–95%0.751348k$0.33 list2
116google/gemini-3.8-flashpi · config da41c66e3 / 4 30%–95%0.751844k$0.53 list1
117fireworks/qwen3.8-maxpi · config da41c66e2 / 3 21%–94%0.731177k$0.27 list0
118google/gemini-3.8-flash @lowantigravity · config 034ed3a10 / 1 0%–79%0.601no passesunknown0
119google/gemini-4-argon @highantigravity · config 034ed3a10 / 1 0%–79%0.601no passesunknown0
120google/gemini-4-argon @mediumantigravity · config 034ed3a10 / 1 0%–79%0.601no passesunknown0
121anthropic/claude-haiku-5-5 @highclaude-code · config c32a950b0 / 1 0%–79%0.601no passesunknown0
122anthropic/claude-haiku-5-5 @maxclaude-code · config c32a950b0 / 1 0%–79%0.601no passesunknown1
123anthropic/claude-haiku-5-5 @xhighclaude-code · config c32a950b0 / 1 0%–79%0.601no passesunknown0
124anthropic/claude-opus-5-5 @lowclaude-code · config c32a950b0 / 1 0%–79%0.801no passesunknown0
125anthropic/claude-sonnet-5-5 @xhighclaude-code · config c32a950b0 / 1 0%–79%0.601no passesunknown0
126baseten/glm-5.3-flashclaude-code · config ecb67e4e0 / 1 0%–79%0.601no passesunknown0
127google/gemini-3.8-flashclaude-code · config ecb67e4e0 / 1 0%–79%1no passesunknown0
128openai/gpt-6-luna @lowclaude-code · config ecb67e4e0 / 1 0%–79%0.401no passesunknown0
129openai/gpt-6-luna @xhighclaude-code · config ecb67e4e0 / 1 0%–79%0.601no passesunknown0
130anthropic/claude-haiku-5-5 @maxcodex · config 3437a9e60 / 1 0%–79%0.601no passesunknown1
131anthropic/claude-sonnet-5-5codex · config 3437a9e60 / 1 0%–79%0.601no passesunknown0
132anthropic/claude-sonnet-5-5 @lowcodex · config 3437a9e60 / 1 0%–79%0.601no passesunknown0
133baseten/glm-5.3-flashcodex · config 3437a9e60 / 1 0%–79%0.601no passesunknown0
134google/gemini-3.8-flash @highcodex · config 3437a9e60 / 1 0%–79%0.601no passesunknown0
135google/gemini-3.8-flash @lowcodex · config 3437a9e60 / 1 0%–79%1no passesunknown0
136moonshot/kimi-k3codex · config 3437a9e60 / 1 0%–79%0.601no passesunknown0
137openai/gpt-5.6-terra @highcodex · config b23964030 / 1 0%–79%0.601no passesunknown0
138openai/gpt-5.6-terra @maxcodex · config b23964030 / 1 0%–79%0.601no passesunknown0
139openai/gpt-5.6-terra @mediumcodex · config b23964030 / 1 0%–79%0.601no passesunknown0
140openai/gpt-5.6-terra @ultracodex · config b23964030 / 1 0%–79%0.601no passesunknown0
141openai/gpt-6-luna @lowcodex · config b23964030 / 1 0%–79%1no passesunknown0
142anthropic/claude-haiku-5-5 @maxopencode · config 357da8910 / 1 0%–79%0.601no passesunknown0
143anthropic/claude-haiku-5-5 @mediumopencode · config 357da8910 / 1 0%–79%0.601no passesunknown0
144anthropic/claude-opus-5-5 @lowopencode · config 357da8910 / 1 0%–79%0.801no passesunknown0
145anthropic/claude-sonnet-5-5 @lowopencode · config 357da8910 / 1 0%–79%0.601no passesunknown0
146anthropic/claude-sonnet-5-5 @mediumopencode · config 357da8910 / 1 0%–79%0.601no passesunknown0
147google/gemini-3.8-flash @lowopencode · config 357da8910 / 1 0%–79%0.601no passesunknown0
148openai/gpt-6-luna @maxopencode · config 357da8910 / 1 0%–79%0.801no passesunknown0
149anthropic/claude-haiku-5-5 @maxpi · config da41c66e0 / 1 0%–79%0.801no passesunknown0
150anthropic/claude-haiku-5-5 @mediumpi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
151anthropic/claude-haiku-5-5 @xhighpi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
152anthropic/claude-sonnet-5-5pi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
153anthropic/claude-sonnet-5-5 @lowpi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
154openai/gpt-5.6-terra @highpi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
155openai/gpt-6-luna @lowpi · config da41c66e0 / 1 0%–79%1no passesunknown0
156zai/glm-5.2pi · config da41c66e0 / 1 0%–79%0.601no passesunknown0
157anthropic/claude-opus-5-5 @maxcodex · config 3437a9e6— 0%–0%0not measured (0/0)unknown2
158anthropic/claude-sonnet-5-5 @maxcodex · config 3437a9e6— 0%–0%0not measured (0/0)unknown1
159google/gemini-3.8-flash @lowpi · config da41c66e— 0%–0%0not measured (0/0)unknown1
list = published-rate · invoice = provider-invoice-reconciled