Board · task version 2

coding

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
  • coding-toc-large-output
coding · task version 2
#Liverymodel · harness · configpassed / n95% Wilsonmeantaskstokens / passcost / passexcluded
1openai/gpt-6.1-sol @mediumcodex · config b239640311 / 11 74%–100%1246k$0.10 list0
2openai/gpt-6.1-sol @highcodex · config b239640310 / 10 72%–100%1305k$0.11 list0
3anthropic/claude-opus-5-5claude-code · config c32a950b6 / 6 61%–100%13.37M$0.86 list0
4anthropic/claude-opus-5-5 @xhighclaude-code · config c32a950b5 / 5 57%–100%13.97M$1.03 list0
5openai/gpt-6.1-solcodex · config b23964035 / 5 57%–100%1254k$0.09 list0
6openai/gpt-6.1-sol @xhighcodex · config b23964035 / 5 57%–100%1310k$0.12 list0
7openai/gpt-6.1-solopencode · config 357da8915 / 5 57%–100%1567k$0.19 list0
8together/deepseek-v4.1-flashpi · config da41c66e5 / 5 57%–100%1325k$0.10 list0
9google/gemini-3.8-flashpi · config da41c66e4 / 4 51%–100%11.06M$0.18 list1
10fireworks/qwen3.8-maxclaude-code · config ecb67e4e3 / 3 44%–100%1882k$0.32 list0
11together/deepseek-v4.1-flashclaude-code · config ecb67e4e3 / 3 44%–100%1679k$0.21 list2
12baseten/glm-5.3-flashpi · config da41c66e3 / 3 44%–100%1382k$0.04 list0
13fireworks/qwen3.8-maxpi · config da41c66e3 / 3 44%–100%1655k$0.29 list0
14google/gemini-3.8-flash @highpi · config da41c66e3 / 3 44%–100%11.76M$0.28 list2
15openai/gpt-6.1-solpi · config da41c66e3 / 3 44%–100%1308k$0.12 list0
16google/gemini-3.1-pro @highantigravity · config 034ed3a11 / 1 21%–100%1196kunknown0
17google/gemini-3.8-flash @highantigravity · config 034ed3a11 / 1 21%–100%11.77M$0.41 list0
18google/gemini-4-argon @highantigravity · config 034ed3a11 / 1 21%–100%1169k$0.12 list0
19anthropic/claude-haiku-4-5claude-code · config c32a950b1 / 1 21%–100%11.13M$0.14 list0
20anthropic/claude-sonnet-5claude-code · config c32a950b1 / 1 21%–100%1991k$0.26 list0
21anthropic/claude-sonnet-5-5claude-code · config c32a950b1 / 1 21%–100%11.92M$0.26 list0
22fireworks/kimi-k3claude-code · config ecb67e4e1 / 1 21%–100%1765k$0.37 list0
23google/gemini-3.8-flash @highclaude-code · config ecb67e4e1 / 1 21%–100%12.93M$0.51 list0
24google/gemini-3.8-flash @lowclaude-code · config ecb67e4e1 / 1 21%–100%1627k$0.13 list0
25google/gemini-3.8-flash @mediumclaude-code · config ecb67e4e1 / 1 21%–100%1524k$0.13 list0
26moonshot/kimi-k3claude-code · config ecb67e4e1 / 1 21%–100%1531k$0.32 list1
27openai/gpt-6.1-solclaude-code · config ecb67e4e1 / 1 21%–100%1425k$0.14 list1
28zai/glm-5.2claude-code · config ecb67e4e1 / 1 21%–100%1679k$0.22 list0
29anthropic/claude-opus-5-5codex · config 3437a9e61 / 1 21%–100%1170k$0.70 list0
30baseten/glm-5.3-flashcodex · config 3437a9e61 / 1 21%–100%1142k$0.02 list0
31fireworks/qwen3.8-maxcodex · config 3437a9e61 / 1 21%–100%1573k$0.32 list0
32google/gemini-3.8-flashcodex · config 3437a9e61 / 1 21%–100%1378k$0.11 list0
33google/gemini-3.8-flash @highcodex · config 3437a9e61 / 1 21%–100%11.90M$0.46 list0
34google/gemini-3.8-flash @lowcodex · config 3437a9e61 / 1 21%–100%1405k$0.09 list0
35moonshot/kimi-k3codex · config 3437a9e61 / 1 21%–100%1109k$0.09 list0
36together/deepseek-v4.1-flashcodex · config 3437a9e61 / 1 21%–100%1130k$0.04 list0
37openai/gpt-6.1-sol @lowcodex · config b23964031 / 1 21%–100%1196k$0.08 list0
38anthropic/claude-opus-5-5opencode · config 357da8911 / 1 21%–100%1351k$0.36 list0
39anthropic/claude-sonnet-5-5opencode · config 357da8911 / 1 21%–100%1202k$0.12 list0
40fireworks/kimi-k3opencode · config 357da8911 / 1 21%–100%1460k$0.41 list0
41fireworks/qwen3.8-maxopencode · config 357da8911 / 1 21%–100%1941k$0.40 list0
42google/gemini-3.8-flashopencode · config 357da8911 / 1 21%–100%114.32M$1.41 list0
43google/gemini-3.8-flash @highopencode · config 357da8911 / 1 21%–100%11.05M$0.19 list0
44google/gemini-3.8-flash @lowopencode · config 357da8911 / 1 21%–100%1786k$0.13 list0
45moonshot/kimi-k3opencode · config 357da8911 / 1 21%–100%1380k$0.29 list0
46zai/glm-5.2opencode · config 357da8911 / 1 21%–100%1437k$0.26 list0
47anthropic/claude-opus-5-5pi · config da41c66e1 / 1 21%–100%1269k$1.09 list0
48anthropic/claude-sonnet-5-5pi · config da41c66e1 / 1 21%–100%1181k$0.37 list0
49fireworks/kimi-k3pi · config da41c66e1 / 1 21%–100%1309k$0.25 list0
50google/gemini-3.8-flash @lowpi · config da41c66e1 / 1 21%–100%1469k$0.09 list0
51moonshot/kimi-k3pi · config da41c66e1 / 1 21%–100%1265k$0.23 list0
52zai/glm-5.2pi · config da41c66e1 / 1 21%–100%1424k$0.24 list0
53fireworks/kimi-k3codex · config 3437a9e62 / 3 21%–94%1195k$0.16 list0
54zai/glm-5.2codex · config 3437a9e62 / 3 21%–94%1289k$0.13 list0
55baseten/glm-5.3-flashopencode · config 357da8911 / 3 6%–79%1667k$0.07 list0
56baseten/glm-5.3-flashclaude-code · config ecb67e4e0 / 1 0%–79%1no passesunknown0
57google/gemini-3.8-flashclaude-code · config ecb67e4e0 / 1 0%–79%1no passesunknown0
58anthropic/claude-sonnet-5-5codex · config 3437a9e60 / 1 0%–79%1no passesunknown0
59together/deepseek-v4.1-flashopencode · config 357da8910 / 1 0%–79%1no passesunknown0
list = published-rate · invoice = provider-invoice-reconciled