| 89cx…mnbz | nvidia_nim | meta/llama-3.1-8b-instruct | freeform-short | 0/13 | n/a | n/a | n/a |
| 89cx…mnbz | nvidia_nim | meta/llama-3.1-8b-instruct | json-extract | 0/13 | n/a | n/a | n/a |
| 89cx…mnbz | nvidia_nim | meta/llama-3.1-8b-instruct | long-generation | 0/13 | n/a | n/a | n/a |
| 89cx…mnbz | nvidia_nim | meta/llama-3.1-8b-instruct | reasoning-arith | 0/13 | n/a | n/a | n/a |
| vx9r…ng6b | openrouter | anthropic/claude-3.5-sonnet | freeform-short | 0/13 | n/a | n/a | n/a |
| vx9r…ng6b | openrouter | anthropic/claude-3.5-sonnet | json-extract | 0/13 | n/a | n/a | n/a |
| vx9r…ng6b | openrouter | anthropic/claude-3.5-sonnet | long-generation | 0/13 | n/a | n/a | n/a |
| vx9r…ng6b | openrouter | anthropic/claude-3.5-sonnet | reasoning-arith | 0/13 | n/a | n/a | n/a |
| mkqm…zrcr | openrouter | google/gemini-2.0-flash-001 | freeform-short | 0/13 | n/a | n/a | n/a |
| mkqm…zrcr | openrouter | google/gemini-2.0-flash-001 | json-extract | 0/13 | n/a | n/a | n/a |
| mkqm…zrcr | openrouter | google/gemini-2.0-flash-001 | long-generation | 0/13 | n/a | n/a | n/a |
| mkqm…zrcr | openrouter | google/gemini-2.0-flash-001 | reasoning-arith | 0/13 | n/a | n/a | n/a |
| 2yze…dnhm | openrouter | meta-llama/llama-3.1-8b-instruct | freeform-short | 13/13 | 31% | No | 5 |
| 2yze…dnhm | openrouter | meta-llama/llama-3.1-8b-instruct | json-extract | 13/13 | 69% | No | 3 |
| 2yze…dnhm | openrouter | meta-llama/llama-3.1-8b-instruct | long-generation | 13/13 | 46% | No | 8 |
| 2yze…dnhm | openrouter | meta-llama/llama-3.1-8b-instruct | reasoning-arith | 13/13 | 31% | No | 6 |
| sdcq…th8x | openrouter | openai/gpt-4o-mini | freeform-short | 13/13 | 31% | No | 8 |
| sdcq…th8x | openrouter | openai/gpt-4o-mini | json-extract | 13/13 | 100% | Yes · byte-exact | 1 |
| sdcq…th8x | openrouter | openai/gpt-4o-mini | long-generation | 13/13 | 8% | No | 13 |
| sdcq…th8x | openrouter | openai/gpt-4o-mini | reasoning-arith | 13/13 | 31% | No | 10 |