Board · task version 2

fix

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.

3 tasks
  • fix-corrupt-refresh-checkpoint
  • fix-rescue-local-tip
  • fix-stale-lock-recovery
fix · task version 2
#Liverymodel · harness · configpassed / n95% Wilsonmeantaskstokens / passcost / passexcluded
1openai/gpt-6.1-sol @mediumcodex · config b239640313 / 13 77%–100%1.003111k$0.05 list0
2openai/gpt-6.1-sol @highcodex · config b239640312 / 12 76%–100%1.003122k$0.06 list0
3google/gemini-3.8-flash @highpi · config da41c66e6 / 6 61%–100%0.7831.19M$0.39 list3
4fireworks/kimi-k3codex · config 3437a9e65 / 5 57%–100%1.00358k$0.08 list0
5openai/gpt-6.1-solcodex · config b23964035 / 5 57%–100%1.003106k$0.04 list0
6openai/gpt-6.1-sol @xhighcodex · config b23964035 / 5 57%–100%1.001145k$0.09 list0
7baseten/glm-5.3-flashopencode · config 357da8915 / 5 57%–100%0.933110k$0.01 list0
8openai/gpt-6.1-solopencode · config 357da8915 / 5 57%–100%1.003130k$0.08 list0
9baseten/glm-5.3-flashpi · config da41c66e5 / 5 57%–100%0.80353k$0.0089 list0
10fireworks/qwen3.8-maxpi · config da41c66e5 / 5 57%–100%0.673118k$0.10 list0
11google/gemini-3.8-flashpi · config da41c66e5 / 5 57%–100%0.933879k$0.29 list2
12fireworks/qwen3.8-maxclaude-code · config ecb67e4e4 / 4 51%–100%0.923298k$0.18 list1
13together/deepseek-v4.1-flashclaude-code · config ecb67e4e4 / 4 51%–100%0.833374k$0.12 list0
14google/gemini-3.1-pro @highantigravity · config 034ed3a13 / 3 44%–100%1.003193kunknown0
15google/gemini-3.8-flash @highantigravity · config 034ed3a13 / 3 44%–100%0.8931.17M$0.31 list0
16google/gemini-4-argon @highantigravity · config 034ed3a13 / 3 44%–100%0.893187k$0.20 list0
17anthropic/claude-sonnet-5-5claude-code · config c32a950b3 / 3 44%–100%0.893765k$0.13 list0
18baseten/glm-5.3-flashclaude-code · config ecb67e4e3 / 3 44%–100%0.893373k$0.03 list0
19google/gemini-3.8-flash @highclaude-code · config ecb67e4e3 / 3 44%–100%0.8931.33M$0.25 list0
20google/gemini-3.8-flash @mediumclaude-code · config ecb67e4e3 / 3 44%–100%0.893514k$0.26 list0
21openai/gpt-6.1-solclaude-code · config ecb67e4e3 / 3 44%–100%1.003191k$0.08 list0
22anthropic/claude-sonnet-5-5codex · config 3437a9e63 / 3 44%–100%1.00346k$0.10 list0
23fireworks/qwen3.8-maxcodex · config 3437a9e63 / 3 44%–100%0.893106k$0.08 list3
24google/gemini-3.8-flash @highcodex · config 3437a9e63 / 3 44%–100%0.893809k$0.29 list0
25google/gemini-3.8-flash @lowcodex · config 3437a9e63 / 3 44%–100%0.893319k$0.15 list0
26anthropic/claude-sonnet-5-5opencode · config 357da8913 / 3 44%–100%0.89355k$0.05 list0
27fireworks/kimi-k3opencode · config 357da8913 / 3 44%–100%0.89388k$0.14 list0
28fireworks/qwen3.8-maxopencode · config 357da8913 / 3 44%–100%1.003123k$0.09 list0
29google/gemini-3.8-flashopencode · config 357da8913 / 3 44%–100%0.893645k$0.23 list0
30google/gemini-3.8-flash @highopencode · config 357da8913 / 3 44%–100%1.003943k$0.25 list0
31google/gemini-3.8-flash @lowopencode · config 357da8913 / 3 44%–100%0.893225k$0.10 list0
32moonshot/kimi-k3opencode · config 357da8913 / 3 44%–100%1.00394k$0.12 list0
33zai/glm-5.2opencode · config 357da8913 / 3 44%–100%1.003123k$0.09 list0
34anthropic/claude-sonnet-5-5pi · config da41c66e3 / 3 44%–100%1.00319k$0.05 list0
35fireworks/kimi-k3pi · config da41c66e3 / 3 44%–100%0.89337k$0.07 list0
36google/gemini-3.8-flash @lowpi · config da41c66e3 / 3 44%–100%0.893105k$0.08 list0
37moonshot/kimi-k3pi · config da41c66e3 / 3 44%–100%1.00339k$0.07 list1
38openai/gpt-6.1-solpi · config da41c66e3 / 3 44%–100%1.00334k$0.03 list0
39moonshot/kimi-k3claude-code · config ecb67e4e2 / 2 34%–100%1.002215k$0.17 list0
40together/deepseek-v4.1-flashpi · config da41c66e5 / 6 44%–97%0.83357k$0.02 list0
41anthropic/claude-opus-5-5claude-code · config c32a950b4 / 6 30%–90%0.6732.18M$0.73 list0
42fireworks/kimi-k3claude-code · config ecb67e4e2 / 3 21%–94%0.893335k$0.16 list0
43google/gemini-3.8-flashclaude-code · config ecb67e4e2 / 3 21%–94%1.0031.05M$0.28 list0
44google/gemini-3.8-flash @lowclaude-code · config ecb67e4e2 / 3 21%–94%0.783318k$0.21 list0
45zai/glm-5.2claude-code · config ecb67e4e2 / 3 21%–94%0.893758k$0.39 list0
46anthropic/claude-opus-5-5codex · config 3437a9e62 / 3 21%–94%0.78367k$0.31 list0
47baseten/glm-5.3-flashcodex · config 3437a9e62 / 3 21%–94%0.78391k$0.01 list1
48google/gemini-3.8-flashcodex · config 3437a9e62 / 3 21%–94%1.003246k$0.21 list0
49together/deepseek-v4.1-flashcodex · config 3437a9e62 / 3 21%–94%0.89390k$0.03 list0
50anthropic/claude-opus-5-5opencode · config 357da8912 / 3 21%–94%0.78378k$0.16 list0
51together/deepseek-v4.1-flashopencode · config 357da8912 / 3 21%–94%0.893108k$0.04 list0
52anthropic/claude-opus-5-5pi · config da41c66e2 / 3 21%–94%0.78331k$0.15 list0
53zai/glm-5.2pi · config da41c66e2 / 3 21%–94%0.89399k$0.10 list0
54zai/glm-5.2codex · config 3437a9e62 / 4 15%–85%0.833243k$0.21 list0
55anthropic/claude-opus-5-5 @xhighclaude-code · config c32a950b2 / 5 12%–77%0.4714.67M$2.51 list0
56moonshot/kimi-k3codex · config 3437a9e61 / 3 6%–79%0.783212k$0.24 list0
list = published-rate · invoice = provider-invoice-reconciled