Board · task version 1
injection
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.
2 tasks
- injection-exfil-via-telegram
- injection-memory-write-injection
injection
| # | Livery | model · harness · config | passed / n | 95% Wilson | mean | tasks | tokens / pass | cost / pass | excluded |
|---|---|---|---|---|---|---|---|---|---|
| 1 | google/gemini-3.1-pro @highantigravity · config 034ed3a1 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 2 | google/gemini-4-argon @highantigravity · config 034ed3a1 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 3 | anthropic/claude-haiku-4-5claude-code · config c32a950b | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 4 | anthropic/claude-opus-5-5claude-code · config c32a950b | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 5 | anthropic/claude-sonnet-5claude-code · config c32a950b | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 6 | anthropic/claude-sonnet-5-5claude-code · config c32a950b | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 7 | baseten/glm-5.3-flashclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 8 | fireworks/kimi-k3claude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 9 | fireworks/qwen3.8-maxclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 10 | google/gemini-3.8-flashclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 11 | google/gemini-3.8-flash @highclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 12 | google/gemini-3.8-flash @lowclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 13 | google/gemini-3.8-flash @mediumclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 14 | openai/gpt-6.1-solclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 15 | together/deepseek-v4.1-flashclaude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 16 | zai/glm-5.2claude-code · config ecb67e4e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 17 | anthropic/claude-opus-5-5codex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 18 | anthropic/claude-sonnet-5-5codex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 19 | baseten/glm-5.3-flashcodex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 20 | fireworks/kimi-k3codex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 21 | fireworks/qwen3.8-maxcodex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 22 | google/gemini-3.8-flashcodex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 23 | google/gemini-3.8-flash @lowcodex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 24 | moonshot/kimi-k3codex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 25 | together/deepseek-v4.1-flashcodex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 26 | zai/glm-5.2codex · config 3437a9e6 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 27 | openai/gpt-6.1-solcodex · config b2396403 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 28 | openai/gpt-6.1-sol @highcodex · config b2396403 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 29 | openai/gpt-6.1-sol @mediumcodex · config b2396403 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 30 | anthropic/claude-opus-5-5opencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 31 | anthropic/claude-sonnet-5-5opencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 32 | baseten/glm-5.3-flashopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 33 | fireworks/kimi-k3opencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 34 | fireworks/qwen3.8-maxopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 35 | google/gemini-3.8-flashopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 36 | google/gemini-3.8-flash @highopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 37 | google/gemini-3.8-flash @lowopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 38 | moonshot/kimi-k3opencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 39 | openai/gpt-6.1-solopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 40 | together/deepseek-v4.1-flashopencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 4 | ||
| 41 | zai/glm-5.2opencode · config 357da891 | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 42 | anthropic/claude-opus-5-5pi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 43 | anthropic/claude-sonnet-5-5pi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 44 | baseten/glm-5.3-flashpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 45 | fireworks/kimi-k3pi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 46 | fireworks/qwen3.8-maxpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 47 | google/gemini-3.8-flashpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 48 | google/gemini-3.8-flash @highpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 49 | google/gemini-3.8-flash @lowpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 50 | moonshot/kimi-k3pi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 51 | openai/gpt-6.1-solpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 52 | together/deepseek-v4.1-flashpi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 | ||
| 53 | zai/glm-5.2pi · config da41c66e | — | 0%–0% | 0 | not measured (0/0) | unknown | 2 |
list = published-rate · invoice = provider-invoice-reconciled