Zabio has not run its own tests on this model. Everything below is aggregated from public benchmarks, with the sources named.
Price against score in each kind of job (2) Price per 1,000 tasks, USD. Score, %. Greyed out: a cheaper model already scores as well. Ringed: the best, balanced and cheap choice.
Writing code, Hard 0 25 50 75 100 $1 $10 $100
deepseek-v4.1-flash-1017@deepinfra: 38.8 +/- 11.5, $0.59
deepseek-flash@deepinfra: 64.4 +/- 11.4, $0.85
claude-haiku-5-5: 63.4 +/- 7.1, $0.88
gpt-6-luna: 25.7 +/- 6.8, $0.88
gemma-4-31b-it: 8.5 +/- 6.6, $0.94
glm-5.3-flash: 20.7 +/- 9.6, $0.98
glm-5.3-flash@deepinfra: 20.7 +/- 9.6, $0.98
minimax-m3.1-flash: 25.7 +/- 10.3, $1.11
minimax-m3.1-flash@parasail: 25.7 +/- 10.3, $1.11
mimo-v2.6-pro: 36.4 +/- 11.3, $1.83
gpt-5.6-luna: 21.1 +/- 9.8, $2.02
deepseek-flash: 64.4 +/- 11.4, $2.22
deepseek-flash@alibaba-intl: 64.4 +/- 11.4, $2.22
deepseek-flash@parasail: 64.4 +/- 11.4, $2.22
deepseek-flash@together: 64.4 +/- 11.4, $2.22
deepseek-v4.1-flash-1017: 38.8 +/- 11.5, $2.22
deepseek-v4.1-flash-1017@parasail: 38.8 +/- 11.5, $2.22
qwen3.8-27b@deepinfra: 15.9 +/- 8.6, $2.83
deepseek-flash-fast@parasail: 64.4 +/- 11.4, $3.33
qwen3.8-27b@parasail: 15.9 +/- 8.6, $3.45
glm-5.2@deepinfra: 36.7 +/- 11.5, $3.56
mistral-large-4-0: 32.4 +/- 7.4, $4.24
qwen3.8-27b: 15.9 +/- 8.6, $5.05
deepseek-v4-pro-0813@deepinfra: 33.3 +/- 10.0, $6.11
gemini-3.8-flash: 27.7 +/- 7.4, $6.56
gemini-3.7-flash: 41.1 +/- 12.2, $6.56
gemini-3.6-flash: 23.3 +/- 9.3, $6.56
inkling: 9.8 +/- 7.0, $7.47
deepseek-v4-pro-0813: 33.3 +/- 10.0, $7.99
glm-5.2: 36.7 +/- 11.5, $8.74
glm-5.2@alibaba-intl: 36.7 +/- 11.5, $8.74
glm-5.2@alibaba-us: 36.7 +/- 11.5, $8.74
gpt-6.1-terra: 66.4 +/- 7.5, $8.75
qwen3.8-max-0902: 37.2 +/- 7.3, $12.10
gemini-4-hydrogen: 61.8 +/- 11.5, $13.13
grok-4.7: 49.9 +/- 8.2, $13.31
grok-4.6: 29.9 +/- 7.2, $13.31
gpt-5: 4.4 +/- 3.4, $16.00
kimi-k3.1-pro@deepinfra: 38.7 +/- 11.5, $16.63
gemini-4-carbon: 72.7 +/- 10.5, $17.50
gpt-6.1-sol: 63.4 +/- 8.0, $17.50
gemini-4-argon: 58.7 +/- 8.3, $17.50
claude-sonnet-5-5: 80.6 +/- 5.7, $17.50
kimi-k3.1-pro: 38.7 +/- 11.5, $17.50
kimi-k3.1-pro@together: 38.7 +/- 11.5, $17.50
gpt-6-sol: 48.9 +/- 11.2, $17.50
claude-sonnet-5: 63.3 +/- 10.7, $17.50
gpt-5.6-terra: 33.5 +/- 8.1, $20.20
gemini-3.1-pro-preview: 8.9 +/- 4.6, $20.20
gpt-5.2: 32.2 +/- 10.0, $22.40
kimi-k3@deepinfra: 45.2 +/- 8.0, $24.94
gpt-5.4: 23.3 +/- 8.1, $25.25
kimi-k3: 45.2 +/- 8.0, $26.25
kimi-k3@moonshot: 45.2 +/- 8.0, $26.25
claude-opus-5-5: 84.2 +/- 5.4, $35.00
gpt-5.6-sol: 20.0 +/- 9.2, $35.00
claude-opus-5: 87.8 +/- 7.2, $43.75
claude-opus-4-7: 43.3 +/- 9.6, $43.75
claude-opus-4-8: 65.6 +/- 10.9, $43.75
claude-opus-4-6: 33.3 +/- 10.0, $43.75
gpt-5.5: 23.3 +/- 10.1, $50.50
claude-fable-5-2: 82.9 +/- 8.9, $70.00
claude-fable-5-1: 83.8 +/- 5.5, $87.50
gpt-6-astra: 67.8 +/- 7.8, $87.50
claude-fable-5: 70.0 +/- 10.4, $87.50
deepseek-flash@deepinfra Cheap gemini-4-carbon Best, Balanced Using tools, Hard 0 25 50 75 100 $1 $10 $100
gpt-oss-20b: 3.1 +/- 1.5, $0.37
gpt-oss-120b@deepinfra: 14.2 +/- 2.3, $0.45
qwen3.5-9b@deepinfra: 9.2 +/- 2.4, $0.67
qwen3.5-9b@parasail: 9.2 +/- 2.4, $0.85
gpt-5-nano: 7.0 +/- 1.9, $0.92
deepseek-v4.1-flash-1017@deepinfra: 38.8 +/- 11.5, $0.92
qwen3.5-9b: 9.2 +/- 2.4, $1.13
claude-haiku-5-5: 47.9 +/- 11.8, $1.30
gpt-6-luna: 24.7 +/- 10.2, $1.30
glm-5.3-flash: 20.7 +/- 9.6, $1.50
glm-5.3-flash@deepinfra: 20.7 +/- 9.6, $1.50
gemma-4-31b-it: 8.5 +/- 6.6, $1.52
minimax-m3.1-flash: 25.7 +/- 10.3, $1.68
minimax-m3.1-flash@parasail: 25.7 +/- 10.3, $1.68
gpt-oss-120b: 14.2 +/- 2.3, $1.68
deepseek-v3.2: 39.6 +/- 2.8, $1.72
qwen3.6-35b-a3b@parasail: 24.6 +/- 3.2, $2.02
qwen3.6-35b-a3b@deepinfra: 24.6 +/- 3.2, $2.11
mimo-v2.6-pro: 36.4 +/- 11.3, $2.96
deepseek-v4.1-flash-1017: 38.8 +/- 11.5, $3.36
deepseek-v4.1-flash-1017@parasail: 38.8 +/- 11.5, $3.36
qwen3.8-27b@deepinfra: 15.9 +/- 8.6, $3.98
gpt-5-mini: 22.3 +/- 2.6, $4.60
glm-4.7: 33.3 +/- 2.5, $4.75
qwen3.8-27b@parasail: 15.9 +/- 8.6, $4.92
qwen3.6-35b-a3b: 24.6 +/- 3.2, $5.55
glm-4.6: 24.5 +/- 2.4, $5.60
mistral-large-4-0: 24.7 +/- 10.2, $6.58
gemini-3-flash-preview: 47.4 +/- 3.0, $7.40
qwen3.8-27b: 15.9 +/- 8.6, $7.40
gemini-3.8-flash: 16.5 +/- 8.8, $9.75
inkling: 9.8 +/- 7.0, $11.29
gpt-6.1-terra: 56.2 +/- 11.7, $13.00
claude-haiku-4-5: 13.9 +/- 2.7, $13.00
qwen3.8-max-0902: 26.6 +/- 10.4, $18.80
gemini-4-hydrogen: 61.8 +/- 11.5, $19.50
grok-4.7: 45.3 +/- 11.7, $20.68
grok-4.6: 18.7 +/- 9.2, $20.68
o3: 9.1 +/- 1.5, $22.40
gpt-5.1: 47.6 +/- 2.8, $23.00
gpt-5: 33.9 +/- 2.9, $23.00
kimi-k3.1-pro@deepinfra: 38.7 +/- 11.5, $24.70
gpt-6.1-sol: 65.6 +/- 11.2, $26.00
claude-sonnet-5-5: 63.4 +/- 11.4, $26.00
gemini-4-carbon: 72.7 +/- 10.5, $26.00
gemini-4-argon: 58.5 +/- 11.6, $26.00
kimi-k3.1-pro: 38.7 +/- 11.5, $26.00
kimi-k3.1-pro@together: 38.7 +/- 11.5, $26.00
gpt-4o: 8.6 +/- 2.1, $28.00
gemini-3.1-pro-preview: 61.4 +/- 4.1, $29.60
gpt-5.6-terra: 25.9 +/- 10.3, $29.60
gpt-5.2: 54.0 +/- 2.9, $32.20
gpt-5.4: 81.8 +/- 2.0, $37.00
kimi-k3@deepinfra: 36.0 +/- 11.3, $37.05
claude-sonnet-4-6: 62.8 +/- 1.8, $39.00
claude-sonnet-4-5: 41.5 +/- 1.9, $39.00
kimi-k3: 36.0 +/- 11.3, $39.00
kimi-k3@moonshot: 36.0 +/- 11.3, $39.00
claude-opus-5-5: 72.8 +/- 10.5, $52.00
claude-opus-4-7: 80.2 +/- 2.1, $65.00
claude-opus-4-6: 69.9 +/- 2.5, $65.00
claude-opus-4-5: 64.7 +/- 1.8, $65.00
gpt-5.5: 66.1 +/- 2.5, $74.00
claude-fable-5-2: 82.9 +/- 8.9, $104
gpt-6-astra: 75.6 +/- 10.1, $130
claude-fable-5-1: 74.2 +/- 10.3, $130
gpt-6.1-terra Cheap claude-fable-5-2 Best, Balanced