- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 pro high
- Build
afi 0.30.0
Observed 60% 1 measured, 1 scored, 1
recorded
Analysis
Compare configurations
Compare scored trial distributions without merging incompatible reviewer tool, cohort, configuration, build, harness, or adapter inputs
Applying URL-backed comparison filters
Filters All reviewers · Recall · All configurations
Recall
Higher is better · sorted high to low · 54 compatible groups · The range uses one shared scale; solid markers are p50 and dashed markers are p95
- afi
| Subject | Compatible group | Scored / recorded | Total bill | Recall |
|---|---|---|---|---|
| proxy | 1 / 1 | $0.1633 | 60% | |
| proxy | 3 / 3 | $0.2368 | 55% | |
| proxy | 1 / 1 | $1.71 | 50% | |
| proxy | 1 / 1 | $0.7954 | 50% | |
| proxy | 3 / 3 | $0.0288 | 45% | |
| proxy | 1 / 1 | $0.7546 | 45% | |
| proxy | 1 / 1 | $0.4240 | 45% | |
| proxy | 1 / 1 | $0.0368 | 45% | |
| proxy | 2 / 2 | $0.1998 | 42.5% | |
| proxy | 1 / 1 | $0.0139 | 40% | |
| proxy | 1 / 1 | $0.1832 | 40% | |
| proxy | 1 / 1 | $0.1575 | 40% | |
| proxy | 3 / 3 | $0.0387 | 40% | |
| proxy | 1 / 1 | $0.0144 | 40% | |
| proxy | 1 / 1 | $0.3550 | 40% | |
| proxy | 1 / 1 | $0.6895 | 40% | |
| proxy | 1 / 1 | $0.0154 | 40% | |
| proxy | 1 / 1 | $0.2732 | 35% | |
| proxy | 2 / 2 | $0.0271 | 35% | |
| proxy | 1 / 1 | $0.2338 | 35% | |
| proxy | 2 / 2 | $2.23 | 35% | |
| proxy | 1 / 1 | $0.9859 | 30% | |
| proxy | 2 / 2 | $0.2424 | 30% | |
| proxy | 1 / 1 | $0.0154 | 30% | |
| proxy | 1 / 1 | $0.3386 | 30% | |
| proxy | 2 / 2 | $0.4659 | 30% | |
| proxy | 1 / 1 | $0.1149 | 30% | |
| proxy | 1 / 1 | $0.1082 | 25% | |
| proxy | 1 / 1 | $0.1377 | 20% | |
| proxy | 1 / 1 | $0.3200 | 20% | |
| proxy | 1 / 1 | $0.0849 | 20% | |
| proxy | 2 / 2 | $0.7268 | 17.5% | |
| proxy | 1 / 1 | $0.0448 | 15% | |
| proxy | 1 / 1 | $0.1978 | 15% | |
| proxy | 1 / 1 | $0.2223 | 15% | |
| proxy | 1 / 1 | $0.6083 | 15% | |
| proxy | 1 / 1 | $0.0587 | 10% | |
| proxy | 1 / 1 | $0.0141 | 5% | |
| proxy | 1 / 1 | $0.1288 | 5% | |
| proxy | 1 / 1 | $0.3047 | 5% | |
| proxy | 1 / 1 | $0.0220 | 0% | |
| proxy | 1 / 1 | $0.1441 | 0% | |
| proxy | 1 / 1 | $0.006218 | 0% | |
| proxy | 2 / 2 | $0.0268 | 0% | |
| proxy | 1 / 1 | $0.0239 | 0% | |
| proxy | 1 / 1 | $0.0216 | 0% | |
| proxy | 1 / 1 | $0.0142 | 0% |
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
- Recall: Not recorded - no scored trials for recall; Total bill: Not recorded - no scored trials for total_bill
Group distribution
Every row uses the same scale for recall
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt 5.6 sol high
- Build
afi 0.30.0
P50 55% P95 59.5% 3 measured, 3 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · fable 5 high
- Build
afi 0.30.0
Observed 50% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · opus 5 high
- Build
afi 0.30.0
Observed 50% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
P50 45% P95 45% 3 measured, 3 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · opus 5 high
- Build
afi 0.30.0
Observed 45% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Google · gemini 3.1 pro preview high
- Build
afi 0.30.0
Observed 45% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k2.7 code high
- Build
afi 0.30.0
Observed 45% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using xAI · grok 4.5 high
- Build
afi 0.30.0
P50 42.5% P95 44.8% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using xAI · grok 4.5 high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt 5.6 luna high
- Build
afi 0.30.0
P50 40% P95 44.5% 3 measured, 3 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k3 high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Google · gemini 3.1 pro preview high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
Observed 40% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k3 high
- Build
afi 0.30.0
Observed 35% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
P50 35% P95 39.5% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt 5.6 terra high
- Build
afi 0.30.0
Observed 35% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · fable 5 high
- Build
afi 0.30.0
P50 35% P95 35% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k2.7 code high
- Build
afi 0.30.0
Observed 30% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt 5.6 terra high
- Build
afi 0.30.0
P50 30% P95 30% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 flash high
- Build
afi 0.30.0
Observed 30% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k3 high
- Build
afi 0.30.0
Observed 30% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Google · gemini 3.7 flash high
- Build
afi 0.30.0
P50 30% P95 34.5% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Moonshot AI · kimi k2.7 code high
- Build
afi 0.30.0
Observed 30% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 pro high
- Build
afi 0.30.0
Observed 25% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.2 high
- Build
afi 0.30.0
Observed 20% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Google · gemini 3.1 pro preview high
- Build
afi 0.30.0
Observed 20% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Minimax · m3 high
- Build
afi 0.30.0
Observed 20% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · sonnet 5 high
- Build
afi 0.30.0
P50 17.5% P95 19.8% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Minimax · m3 high
- Build
afi 0.30.0
Observed 15% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.2 high
- Build
afi 0.30.0
Observed 15% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.2 high
- Build
afi 0.30.0
Observed 15% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Google · gemini 3.7 flash high
- Build
afi 0.30.0
Observed 15% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Minimax · m3 high
- Build
afi 0.30.0
Observed 10% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 flash high
- Build
afi 0.30.0
Observed 5% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 pro high
- Build
afi 0.30.0
Observed 5% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 high
- Build
afi 0.30.0
Observed 5% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 flash high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 5.3 high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using DeepSeek · v4 flash high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt oss 120b high
- Build
afi 0.30.0
P50 0% P95 0% 2 measured, 2 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 4.7 flash high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using OpenAI · gpt oss 120b high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Z.AI · glm 4.7 flash high
- Build
afi 0.30.0
Observed 0% 1 measured, 1 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Meta · llama 4 maverick high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Mistral AI · devstral 2512 high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Mistral AI · devstral 2512 high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 2
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · opus 5 high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 1
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Qwen · qwen3 coder 30b a3b instruct high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Qwen · qwen3.7 flash high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 3
recorded
- Subject
- proxy
- Reviewer
- afi afi · cli
- Configuration
- default Default profile using Anthropic · opus 5 high
- Build
afi 0.30.0
Not recorded no scored trials for recall 0 measured, 0 scored, 1
recorded
| Reviewer | Configuration | Build | Measured | Scored | Recorded | Min | P50 ↓ | P95 | Max | Availability | Compatibility identity | View group |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| afi afi · cli | default Default profile / DeepSeek · v4 pro high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 60% | 60% | 60% | 60% | Measured | comparison-2069962f2ec1aa4a | View group |
| afi afi · cli | default Default profile / OpenAI · gpt 5.6 sol high | afi 0.30.0bench 1 / afi 1 | 3 | 3 | 3 | 55% | 55% | 59.5% | 60% | Measured | comparison-004ca4a8ec71f5cd | View group |
| afi afi · cli | default Default profile / Anthropic · fable 5 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 50% | 50% | 50% | 50% | Measured | comparison-3f421c0960d73d4c | View group |
| afi afi · cli | default Default profile / Anthropic · opus 5 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 50% | 50% | 50% | 50% | Measured | comparison-ca02d21e3600cf86 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 3 | 3 | 3 | 35% | 45% | 45% | 45% | Measured | comparison-491a157d4c780a6f | View group |
| afi afi · cli | default Default profile / Anthropic · opus 5 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 45% | 45% | 45% | 45% | Measured | comparison-5481b1a296f22243 | View group |
| afi afi · cli | default Default profile / Google · gemini 3.1 pro preview high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 45% | 45% | 45% | 45% | Measured | comparison-925a9641d42ce469 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k2.7 code high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 45% | 45% | 45% | 45% | Measured | comparison-dca0df8a4b0484b4 | View group |
| afi afi · cli | default Default profile / xAI · grok 4.5 high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 40% | 42.5% | 44.8% | 45% | Measured | comparison-041168a6e4dbca97 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-0c0e860f8f5a8c1d | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-1a363c7589fb1425 | View group |
| afi afi · cli | default Default profile / xAI · grok 4.5 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-208b6b683dd12ab2 | View group |
| afi afi · cli | default Default profile / OpenAI · gpt 5.6 luna high | afi 0.30.0bench 1 / afi 1 | 3 | 3 | 3 | 40% | 40% | 44.5% | 45% | Measured | comparison-2f7717ed5785716d | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-424dd136bef4eaf5 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-908a56c0f29bc097 | View group |
| afi afi · cli | default Default profile / Google · gemini 3.1 pro preview high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-9a3d8931bc48d334 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 40% | 40% | 40% | 40% | Measured | comparison-e88d02a8e3762967 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 35% | 35% | 35% | 35% | Measured | comparison-222854e89c33b7aa | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 30% | 35% | 39.5% | 40% | Measured | comparison-485020d36bca168c | View group |
| afi afi · cli | default Default profile / OpenAI · gpt 5.6 terra high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 35% | 35% | 35% | 35% | Measured | comparison-5e375ce1a3d1f0fc | View group |
| afi afi · cli | default Default profile / Anthropic · fable 5 high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 35% | 35% | 35% | 35% | Measured | comparison-6173376f94cdba42 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k2.7 code high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 30% | 30% | 30% | 30% | Measured | comparison-14cee6e10514f39e | View group |
| afi afi · cli | default Default profile / OpenAI · gpt 5.6 terra high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 30% | 30% | 30% | 30% | Measured | comparison-27c23a88582a4ec5 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 30% | 30% | 30% | 30% | Measured | comparison-4c9e812aab376442 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 30% | 30% | 30% | 30% | Measured | comparison-78f32eae2b308e59 | View group |
| afi afi · cli | default Default profile / Google · gemini 3.7 flash high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 25% | 30% | 34.5% | 35% | Measured | comparison-99aa0f2063f28380 | View group |
| afi afi · cli | default Default profile / Moonshot AI · kimi k2.7 code high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 30% | 30% | 30% | 30% | Measured | comparison-a5b4262e3ada583f | View group |
| afi afi · cli | default Default profile / DeepSeek · v4 pro high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 25% | 25% | 25% | 25% | Measured | comparison-27233269bfca96e3 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.2 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 20% | 20% | 20% | 20% | Measured | comparison-091a12983a62a829 | View group |
| afi afi · cli | default Default profile / Google · gemini 3.1 pro preview high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 20% | 20% | 20% | 20% | Measured | comparison-967db4e472922cb8 | View group |
| afi afi · cli | default Default profile / Minimax · m3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 20% | 20% | 20% | 20% | Measured | comparison-cf0749903d73090c | View group |
| afi afi · cli | default Default profile / Anthropic · sonnet 5 high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 15% | 17.5% | 19.8% | 20% | Measured | comparison-9b0e1ce26d2e951b | View group |
| afi afi · cli | default Default profile / Minimax · m3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 15% | 15% | 15% | 15% | Measured | comparison-1408f01117f795c2 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.2 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 15% | 15% | 15% | 15% | Measured | comparison-21fa35272c82669c | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.2 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 15% | 15% | 15% | 15% | Measured | comparison-65866118b808fcc2 | View group |
| afi afi · cli | default Default profile / Google · gemini 3.7 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 15% | 15% | 15% | 15% | Measured | comparison-de05c76a71b88649 | View group |
| afi afi · cli | default Default profile / Minimax · m3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 10% | 10% | 10% | 10% | Measured | comparison-5b85997dcbcaa859 | View group |
| afi afi · cli | default Default profile / DeepSeek · v4 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 5% | 5% | 5% | 5% | Measured | comparison-6fefa5f4a114931f | View group |
| afi afi · cli | default Default profile / DeepSeek · v4 pro high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 5% | 5% | 5% | 5% | Measured | comparison-d1c302dcee5c202e | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 5% | 5% | 5% | 5% | Measured | comparison-e95fc90e0b08c640 | View group |
| afi afi · cli | default Default profile / DeepSeek · v4 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-159153dbc75bc09b | View group |
| afi afi · cli | default Default profile / Z.AI · glm 5.3 high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-2310e8490e735a16 | View group |
| afi afi · cli | default Default profile / DeepSeek · v4 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-28d6d81900ed09da | View group |
| afi afi · cli | default Default profile / OpenAI · gpt oss 120b high | afi 0.30.0bench 1 / afi 1 | 2 | 2 | 2 | 0% | 0% | 0% | 0% | Measured | comparison-6e2a62fcdcabecf2 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 4.7 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-87fb5cca87b5297b | View group |
| afi afi · cli | default Default profile / OpenAI · gpt oss 120b high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-bcd000be91c9bd81 | View group |
| afi afi · cli | default Default profile / Z.AI · glm 4.7 flash high | afi 0.30.0bench 1 / afi 1 | 1 | 1 | 1 | 0% | 0% | 0% | 0% | Measured | comparison-cdc6b4c79792fb9b | View group |
| afi afi · cli | default Default profile / Meta · llama 4 maverick high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 3 | - | - | - | - | Not recorded no scored trials for recall 3 comparison diagnostics | comparison-0a66a577fd979902 | View group |
| afi afi · cli | default Default profile / Mistral AI · devstral 2512 high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 1 | - | - | - | - | Not recorded no scored trials for recall 1 comparison diagnostic | comparison-1295edd24f1a60bb | View group |
| afi afi · cli | default Default profile / Mistral AI · devstral 2512 high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 2 | - | - | - | - | Not recorded no scored trials for recall 2 comparison diagnostics | comparison-716a72ccfb5b7a10 | View group |
| afi afi · cli | default Default profile / Anthropic · opus 5 high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 1 | - | - | - | - | Not recorded no scored trials for recall 1 comparison diagnostic | comparison-820b84b160b8dcc0 | View group |
| afi afi · cli | default Default profile / Qwen · qwen3 coder 30b a3b instruct high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 3 | - | - | - | - | Not recorded no scored trials for recall 3 comparison diagnostics | comparison-8be3c332d33c58a4 | View group |
| afi afi · cli | default Default profile / Qwen · qwen3.7 flash high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 3 | - | - | - | - | Not recorded no scored trials for recall 3 comparison diagnostics | comparison-b1ff119345b912a5 | View group |
| afi afi · cli | default Default profile / Anthropic · opus 5 high | afi 0.30.0bench 1 / afi 1 | 0 | 0 | 1 | - | - | - | - | Not recorded no scored trials for recall 1 comparison diagnostic | comparison-ccfb78313e2a9558 | View group |
Reviewer tool, configuration settings, build, harness, adapter, reviewed SHA, or answer-key fingerprint changes create a separate row