Open beta Zabio is in open beta: anyone can sign up and use it in production. Models, prices and features can still change while we learn from the first customers. Tell us what breaks at hello@zabio.ai.

Model

deepseek-v4-flash-vision-exp

deepseek-v4-flash-vision-exp from DeepSeek, Fast class. List prices per million tokens, and what the public benchmarks say about it.

Class
Fast
Input, per million
$0.22
Output, per million
$0.65
Cached input
$0.01
Context window
131,072
Longest answer
16,384
Processed by
DeepInfra, Not guaranteed
Processed in
global
Prices from
28 October 2026

Calling it

Name it in the model field, or let auto choose it for you.

"model": "deepseek-v4-flash-vision-exp"

auto can pick this model when it suits the job and the line you chose.

What it costs

  • Input $0.22 and output $0.65 per million tokens, at the provider list price.
  • Input read from cache: $0.01 per million tokens.

Public results for this model

Zabio has not run its own tests on this model. Everything below is aggregated from public benchmarks, with the sources named.

Aggregated from public resultsRead on 16 November 2026

deepseek-v4-flash-vision-exp
Writing, Medium: 76.6 +/- 3.5 Evidence, in standard errors: 0.7 LiveBench Language: 80.4 (Same settings as ours) LiveBench paraphrase: 72.8 (Same settings as ours)Writing, Medium76.6Creative writing, Medium: 73.8 +/- 6.2 Evidence, in standard errors: 0.4 LiveBench story generation: 73.8 (Same settings as ours)Creative writing, Medium73.8Summarizing, Medium: 72.1 +/- 6.3 Evidence, in standard errors: 0.3 LiveBench summarize: 72.1 (Same settings as ours)Summarizing, Medium72.1Sorting into categories, Medium: 71.0 +/- 3.2 Evidence, in standard errors: 0.9 LiveBench IF: 71.0 (Same settings as ours)Sorting into categories, Medium71.0Math, Hard: 87.8 +/- 1.7 Evidence, in standard errors: 0.6 LiveBench Mathematics: 87.8 (Same settings as ours)Math, Hard87.8
The benchmarks behind each bar
Kind of jobBenchmarkScoreSettings
Writing, MediumLiveBench Language80.4Same settings as ours
Writing, MediumLiveBench paraphrase72.8Same settings as ours
Creative writing, MediumLiveBench story generation73.8Same settings as ours
Summarizing, MediumLiveBench summarize72.1Same settings as ours
Sorting into categories, MediumLiveBench IF71.0Same settings as ours
Math, HardLiveBench Mathematics87.8Same settings as ours
Price against score in each kind of job (5)

Price per 1,000 tasks, USD. Score, %. Greyed out: a cheaper model already scores as well. Ringed: the best, balanced and cheap choice.

Writing, Medium
5060708090100$0.1$1$10 deepseek-v4-flash-0731@deepinfra: 70.4 +/- 3.8, $0.12 deepseek-v4-flash@deepinfra: 66.3 +/- 3.9, $0.14 deepseek-v4-flash@parasail: 66.3 +/- 3.9, $0.22 deepseek-v4-flash-0731: 70.4 +/- 3.8, $0.22 deepseek-v4-flash-0731@parasail: 70.4 +/- 3.8, $0.22 deepseek-flash@deepinfra: 76.0 +/- 3.6, $0.28 gpt-6-luna: 61.8 +/- 4.0, $0.28 claude-haiku-5-5: 63.0 +/- 4.0, $0.28 glm-5.3-flash: 62.7 +/- 3.9, $0.32 glm-5.3-flash@deepinfra: 62.7 +/- 3.9, $0.32 deepseek-v4-flash: 66.3 +/- 3.9, $0.32 deepseek-v4-flash-vision-exp: 76.6 +/- 3.5, $0.43 gpt-5.6-luna: 60.2 +/- 4.0, $0.64 gpt-5.4-nano: 64.6 +/- 3.9, $0.66 minimax-m3@deepinfra: 66.4 +/- 3.9, $0.66 deepseek-flash: 76.0 +/- 3.6, $0.72 deepseek-flash@alibaba-intl: 76.0 +/- 3.6, $0.72 deepseek-flash@parasail: 76.0 +/- 3.6, $0.72 deepseek-flash@together: 76.0 +/- 3.6, $0.72 minimax-m3: 66.4 +/- 3.9, $0.72 minimax-m3@parasail: 66.4 +/- 3.9, $0.72 qwen3.8-27b@deepinfra: 74.6 +/- 3.6, $0.87 deepseek-v4-flash-0731@alibaba-intl: 70.4 +/- 3.8, $0.88 qwen3.8-27b@parasail: 74.6 +/- 3.6, $1.07 deepseek-flash-fast@parasail: 76.0 +/- 3.6, $1.08 minimax-m3-fast@parasail: 66.4 +/- 3.9, $1.08 glm-5.2@deepinfra: 69.3 +/- 3.9, $1.17 gemini-3.5-flash-lite: 68.4 +/- 3.8, $1.24 glm-5.3@deepinfra: 72.3 +/- 3.8, $1.45 qwen3.6-27b@deepinfra: 56.4 +/- 4.1, $1.54 qwen3.8-27b: 74.6 +/- 3.6, $1.60 qwen3.6-plus: 67.8 +/- 3.9, $1.60 qwen3.6-27b: 56.4 +/- 4.1, $1.92 kimi-k2.6: 68.4 +/- 3.9, $2.00 deepseek-v4-pro-0813@deepinfra: 75.4 +/- 3.6, $2.08 deepseek-v4-pro@deepinfra: 67.2 +/- 3.9, $2.08 gemini-3.8-flash: 83.9 +/- 3.1, $2.10 gemini-3.7-flash: 81.8 +/- 3.3, $2.10 gemini-3.6-flash: 79.1 +/- 3.4, $2.10 gemini-3.5-flash: 80.1 +/- 3.4, $2.10 kimi-k2.7-code: 63.2 +/- 3.9, $2.36 gpt-5.4-mini: 64.9 +/- 3.9, $2.40 inkling: 72.2 +/- 3.7, $2.42 deepseek-v4-pro-0813: 75.4 +/- 3.6, $2.64 deepseek-v4-pro: 67.2 +/- 3.9, $2.64 deepseek-v4-pro@parasail: 67.2 +/- 3.9, $2.64 deepseek-v4-pro@together: 67.2 +/- 3.9, $2.64 glm-5.3: 72.3 +/- 3.8, $2.88 glm-5.3@alibaba-intl: 72.3 +/- 3.8, $2.88 glm-5.3@parasail: 72.3 +/- 3.8, $2.88 glm-5.2: 69.3 +/- 3.9, $2.88 glm-5.2@alibaba-intl: 69.3 +/- 3.9, $2.88 glm-5.2@alibaba-us: 69.3 +/- 3.9, $2.88 deepseek-v4-pro-fast@parasail: 67.2 +/- 3.9, $3.96 qwen3.8-max-0902: 76.5 +/- 3.5, $4.00 glm-5.3-fast@parasail: 72.3 +/- 3.8, $4.32 grok-4.6: 77.7 +/- 3.5, $4.40 grok-4.7: 79.1 +/- 3.4, $4.40 qwen3.7-max: 75.9 +/- 3.6, $5.00 qwen3.7-max@alibaba-us: 75.9 +/- 3.6, $5.00 gpt-6.1-sol: 81.4 +/- 3.4, $5.60 gpt-6-sol: 77.7 +/- 3.6, $5.60 claude-sonnet-5-5: 63.1 +/- 3.9, $5.60 claude-sonnet-5: 68.1 +/- 3.9, $5.60 gemini-3.1-pro-preview: 82.6 +/- 3.2, $6.40 gpt-5.6-terra: 70.0 +/- 3.8, $6.40 gpt-5.2: 72.0 +/- 3.8, $7.00 kimi-k3@deepinfra: 80.0 +/- 3.4, $7.98 gpt-5.4: 73.0 +/- 3.7, $8.00 kimi-k3: 80.0 +/- 3.4, $8.40 kimi-k3@moonshot: 80.0 +/- 3.4, $8.40 claude-sonnet-4-6: 67.8 +/- 3.9, $8.40 gpt-5.6-sol: 79.6 +/- 3.5, $11.20 claude-opus-5-5: 75.3 +/- 3.7, $11.20 claude-opus-5: 77.2 +/- 3.6, $14.00 claude-opus-4-6: 73.1 +/- 3.7, $14.00 claude-opus-4-7: 71.8 +/- 3.8, $14.00 claude-opus-4-8: 73.8 +/- 3.7, $14.00 claude-opus-4-5: 73.5 +/- 3.7, $14.00 gpt-5.5: 79.6 +/- 3.5, $16.00 claude-fable-5: 84.2 +/- 3.2, $28.00 claude-fable-5-1: 80.5 +/- 3.4, $28.00 gpt-6-astra: 83.8 +/- 3.2, $28.00 deepseek-v4-flash-vision-expgemini-3.8-flash Cheapclaude-fable-5 Best, Balanced
Creative writing, Medium
0255075100$0.1$1$10 deepseek-v4-flash-0731@deepinfra: 70.5 +/- 6.5, $0.12 deepseek-v4-flash@deepinfra: 67.3 +/- 6.6, $0.14 deepseek-v4-flash@parasail: 67.3 +/- 6.6, $0.22 deepseek-v4-flash-0731: 70.5 +/- 6.5, $0.22 deepseek-v4-flash-0731@parasail: 70.5 +/- 6.5, $0.22 deepseek-flash@deepinfra: 72.7 +/- 6.3, $0.28 gpt-6-luna: 63.3 +/- 6.8, $0.28 claude-haiku-5-5: 73.6 +/- 6.2, $0.28 glm-5.3-flash: 59.9 +/- 6.9, $0.32 glm-5.3-flash@deepinfra: 59.9 +/- 6.9, $0.32 deepseek-v4-flash: 67.3 +/- 6.6, $0.32 deepseek-v4-flash-vision-exp: 73.8 +/- 6.2, $0.43 gpt-5.6-luna: 69.1 +/- 6.5, $0.64 gpt-5.4-nano: 67.7 +/- 6.6, $0.66 minimax-m3@deepinfra: 63.6 +/- 6.8, $0.66 deepseek-flash: 72.7 +/- 6.3, $0.72 deepseek-flash@alibaba-intl: 72.7 +/- 6.3, $0.72 deepseek-flash@parasail: 72.7 +/- 6.3, $0.72 deepseek-flash@together: 72.7 +/- 6.3, $0.72 minimax-m3: 63.6 +/- 6.8, $0.72 minimax-m3@parasail: 63.6 +/- 6.8, $0.72 qwen3.8-27b@deepinfra: 73.1 +/- 6.3, $0.87 deepseek-v4-flash-0731@alibaba-intl: 70.5 +/- 6.5, $0.88 qwen3.8-27b@parasail: 73.1 +/- 6.3, $1.07 deepseek-flash-fast@parasail: 72.7 +/- 6.3, $1.08 minimax-m3-fast@parasail: 63.6 +/- 6.8, $1.08 glm-5.2@deepinfra: 62.9 +/- 6.8, $1.17 gemini-3.5-flash-lite: 67.5 +/- 6.6, $1.24 glm-5.3@deepinfra: 72.1 +/- 6.3, $1.45 qwen3.6-27b@deepinfra: 60.1 +/- 6.9, $1.54 qwen3.6-plus: 56.9 +/- 7.0, $1.60 qwen3.8-27b: 73.1 +/- 6.3, $1.60 qwen3.6-27b: 60.1 +/- 6.9, $1.92 kimi-k2.6: 66.9 +/- 6.7, $2.00 deepseek-v4-pro-0813@deepinfra: 74.9 +/- 6.1, $2.08 deepseek-v4-pro@deepinfra: 67.8 +/- 6.6, $2.08 gemini-3.8-flash: 82.8 +/- 5.3, $2.10 gemini-3.7-flash: 82.3 +/- 5.4, $2.10 gemini-3.6-flash: 75.6 +/- 6.1, $2.10 gemini-3.5-flash: 75.2 +/- 6.1, $2.10 kimi-k2.7-code: 68.6 +/- 6.6, $2.36 gpt-5.4-mini: 66.6 +/- 6.7, $2.40 inkling: 74.2 +/- 6.2, $2.42 deepseek-v4-pro-0813: 74.9 +/- 6.1, $2.64 deepseek-v4-pro: 67.8 +/- 6.6, $2.64 deepseek-v4-pro@parasail: 67.8 +/- 6.6, $2.64 deepseek-v4-pro@together: 67.8 +/- 6.6, $2.64 glm-5.3: 72.1 +/- 6.3, $2.88 glm-5.3@alibaba-intl: 72.1 +/- 6.3, $2.88 glm-5.3@parasail: 72.1 +/- 6.3, $2.88 glm-5.2: 62.9 +/- 6.8, $2.88 glm-5.2@alibaba-intl: 62.9 +/- 6.8, $2.88 glm-5.2@alibaba-us: 62.9 +/- 6.8, $2.88 deepseek-v4-pro-fast@parasail: 67.8 +/- 6.6, $3.96 qwen3.8-max-0902: 76.5 +/- 6.0, $4.00 glm-5.3-fast@parasail: 72.1 +/- 6.3, $4.32 grok-4.6: 78.3 +/- 5.8, $4.40 grok-4.7: 74.9 +/- 6.1, $4.40 qwen3.7-max: 76.3 +/- 6.0, $5.00 qwen3.7-max@alibaba-us: 76.3 +/- 6.0, $5.00 claude-sonnet-5-5: 69.9 +/- 6.5, $5.60 gpt-6.1-sol: 70.8 +/- 6.4, $5.60 gpt-6-sol: 66.9 +/- 6.7, $5.60 claude-sonnet-5: 62.3 +/- 6.9, $5.60 gemini-3.1-pro-preview: 77.3 +/- 5.9, $6.40 gpt-5.6-terra: 66.8 +/- 6.7, $6.40 gpt-5.2: 65.7 +/- 6.7, $7.00 kimi-k3@deepinfra: 75.4 +/- 6.1, $7.98 gpt-5.4: 79.0 +/- 5.8, $8.00 kimi-k3: 75.4 +/- 6.1, $8.40 kimi-k3@moonshot: 75.4 +/- 6.1, $8.40 claude-sonnet-4-6: 68.9 +/- 6.6, $8.40 claude-opus-5-5: 70.9 +/- 6.4, $11.20 gpt-5.6-sol: 75.9 +/- 6.1, $11.20 claude-opus-4-8: 80.6 +/- 5.6, $14.00 claude-opus-4-7: 69.4 +/- 6.5, $14.00 claude-opus-4-6: 66.1 +/- 6.7, $14.00 claude-opus-4-5: 65.9 +/- 6.7, $14.00 claude-opus-5: 61.3 +/- 6.9, $14.00 gpt-5.5: 72.6 +/- 6.3, $16.00 claude-fable-5-1: 78.1 +/- 5.9, $28.00 claude-fable-5: 71.7 +/- 6.4, $28.00 gpt-6-astra: 74.0 +/- 6.2, $28.00 deepseek-v4-flash-0731@deepinfra Cheapdeepseek-v4-flash-vision-expgemini-3.8-flash Best, Balanced
Summarizing, Medium
0255075100$0.1$1$10 deepseek-v4-flash-0731@deepinfra: 71.5 +/- 6.4, $0.18 deepseek-v4-flash@deepinfra: 68.9 +/- 6.6, $0.25 claude-haiku-5-5: 67.0 +/- 6.7, $0.34 gpt-6-luna: 55.3 +/- 7.0, $0.34 deepseek-v4-flash-0731: 71.5 +/- 6.4, $0.39 deepseek-v4-flash-0731@parasail: 71.5 +/- 6.4, $0.39 deepseek-v4-flash@parasail: 68.9 +/- 6.6, $0.39 deepseek-flash@deepinfra: 69.7 +/- 6.5, $0.42 glm-5.3-flash: 56.5 +/- 7.0, $0.46 glm-5.3-flash@deepinfra: 56.5 +/- 7.0, $0.46 deepseek-v4-flash: 68.9 +/- 6.6, $0.56 deepseek-v4-flash-vision-exp: 72.1 +/- 6.3, $0.65 gpt-5.6-luna: 64.9 +/- 6.8, $0.72 gpt-5.4-nano: 71.8 +/- 6.4, $0.73 qwen3.8-27b@deepinfra: 75.9 +/- 6.1, $0.74 minimax-m3@deepinfra: 53.9 +/- 7.1, $0.89 deepseek-flash: 69.7 +/- 6.5, $0.96 deepseek-flash@alibaba-intl: 69.7 +/- 6.5, $0.96 deepseek-flash@parasail: 69.7 +/- 6.5, $0.96 deepseek-flash@together: 69.7 +/- 6.5, $0.96 minimax-m3: 53.9 +/- 7.1, $0.96 minimax-m3@parasail: 53.9 +/- 7.1, $0.96 qwen3.8-27b@parasail: 75.9 +/- 6.1, $1.02 gemini-3.5-flash-lite: 68.5 +/- 6.6, $1.22 deepseek-v4-flash-0731@alibaba-intl: 71.5 +/- 6.4, $1.32 qwen3.6-27b@deepinfra: 52.6 +/- 7.1, $1.41 deepseek-flash-fast@parasail: 69.7 +/- 6.5, $1.44 minimax-m3-fast@parasail: 53.9 +/- 7.1, $1.44 glm-5.2@deepinfra: 68.4 +/- 6.6, $1.71 qwen3.8-27b: 75.9 +/- 6.1, $1.80 qwen3.6-plus: 64.3 +/- 6.8, $1.80 glm-5.3@deepinfra: 74.6 +/- 6.2, $1.85 qwen3.6-27b: 52.6 +/- 7.1, $2.16 kimi-k2.6: 67.5 +/- 6.6, $2.50 gemini-3.8-flash: 87.5 +/- 4.7, $2.55 gemini-3.7-flash: 84.8 +/- 5.1, $2.55 gemini-3.5-flash: 82.6 +/- 5.4, $2.55 gemini-3.6-flash: 75.9 +/- 6.1, $2.55 gpt-5.4-mini: 59.6 +/- 6.9, $2.70 kimi-k2.7-code: 58.3 +/- 7.0, $3.08 inkling: 74.9 +/- 6.1, $3.21 deepseek-v4-pro@deepinfra: 69.5 +/- 6.5, $3.64 deepseek-v4-pro-0813@deepinfra: 65.7 +/- 6.7, $3.64 deepseek-v4-pro: 69.5 +/- 6.5, $3.96 deepseek-v4-pro@parasail: 69.5 +/- 6.5, $3.96 deepseek-v4-pro@together: 69.5 +/- 6.5, $3.96 deepseek-v4-pro-0813: 65.7 +/- 6.7, $3.96 glm-5.3: 74.6 +/- 6.2, $4.24 glm-5.3@alibaba-intl: 74.6 +/- 6.2, $4.24 glm-5.3@parasail: 74.6 +/- 6.2, $4.24 glm-5.2: 68.4 +/- 6.6, $4.24 glm-5.2@alibaba-intl: 68.4 +/- 6.6, $4.24 glm-5.2@alibaba-us: 68.4 +/- 6.6, $4.24 deepseek-v4-pro-fast@parasail: 69.5 +/- 6.5, $5.94 qwen3.8-max-0902: 79.2 +/- 5.8, $6.00 glm-5.3-fast@parasail: 74.6 +/- 6.2, $6.36 grok-4.7: 78.2 +/- 5.8, $6.60 grok-4.6: 68.1 +/- 6.6, $6.60 gpt-6.1-sol: 81.3 +/- 5.5, $6.80 claude-sonnet-5: 71.2 +/- 6.4, $6.80 gpt-6-sol: 68.0 +/- 6.6, $6.80 claude-sonnet-5-5: 58.2 +/- 7.0, $6.80 gpt-5.2: 63.2 +/- 6.8, $7.00 gemini-3.1-pro-preview: 88.2 +/- 4.6, $7.20 gpt-5.6-terra: 73.2 +/- 6.3, $7.20 qwen3.7-max: 83.8 +/- 5.2, $7.50 qwen3.7-max@alibaba-us: 83.8 +/- 5.2, $7.50 gpt-5.4: 68.4 +/- 6.6, $9.00 kimi-k3@deepinfra: 69.4 +/- 6.5, $9.69 kimi-k3: 69.4 +/- 6.5, $10.20 kimi-k3@moonshot: 69.4 +/- 6.5, $10.20 claude-sonnet-4-6: 61.7 +/- 6.9, $10.20 gpt-5.6-sol: 69.4 +/- 6.5, $13.60 claude-opus-5-5: 69.1 +/- 6.5, $13.60 claude-opus-4-8: 77.7 +/- 5.9, $17.00 claude-opus-5: 66.4 +/- 6.7, $17.00 claude-opus-4-7: 66.3 +/- 6.7, $17.00 claude-opus-4-6: 65.2 +/- 6.7, $17.00 claude-opus-4-5: 63.7 +/- 6.8, $17.00 gpt-5.5: 72.3 +/- 6.3, $18.00 claude-fable-5: 81.7 +/- 5.5, $34.00 gpt-6-astra: 79.6 +/- 5.7, $34.00 claude-fable-5-1: 72.2 +/- 6.3, $34.00 deepseek-v4-flash-vision-exp Cheapqwen3.8-27b@deepinfra Balancedgemini-3.8-flash Best
Sorting into categories, Medium
0255075100$0.1$1$10 deepseek-v4-flash-0731@deepinfra: 65.5 +/- 3.4, $0.08 deepseek-v4-flash@deepinfra: 63.1 +/- 3.4, $0.11 deepseek-v4-flash-0731: 65.5 +/- 3.4, $0.17 deepseek-v4-flash-0731@parasail: 65.5 +/- 3.4, $0.17 deepseek-v4-flash@parasail: 63.1 +/- 3.4, $0.17 claude-haiku-5-5: 66.5 +/- 3.3, $0.18 gpt-6-luna: 55.9 +/- 3.5, $0.18 deepseek-flash@deepinfra: 70.0 +/- 3.2, $0.20 glm-5.3-flash: 52.8 +/- 3.5, $0.22 glm-5.3-flash@deepinfra: 52.8 +/- 3.5, $0.22 deepseek-v4-flash: 63.1 +/- 3.4, $0.24 deepseek-v4-flash-vision-exp: 71.0 +/- 3.2, $0.30 gpt-5.6-luna: 60.1 +/- 3.5, $0.40 gpt-5.4-nano: 67.2 +/- 3.3, $0.41 minimax-m3@deepinfra: 57.5 +/- 3.5, $0.44 deepseek-flash: 70.0 +/- 3.2, $0.48 deepseek-flash@alibaba-intl: 70.0 +/- 3.2, $0.48 deepseek-flash@parasail: 70.0 +/- 3.2, $0.48 deepseek-flash@together: 70.0 +/- 3.2, $0.48 minimax-m3: 57.5 +/- 3.5, $0.48 minimax-m3@parasail: 57.5 +/- 3.5, $0.48 qwen3.8-27b@deepinfra: 72.7 +/- 3.2, $0.50 deepseek-v4-flash-0731@alibaba-intl: 65.5 +/- 3.4, $0.62 qwen3.8-27b@parasail: 72.7 +/- 3.2, $0.63 deepseek-flash-fast@parasail: 70.0 +/- 3.2, $0.72 minimax-m3-fast@parasail: 57.5 +/- 3.5, $0.72 gemini-3.5-flash-lite: 67.2 +/- 3.3, $0.74 glm-5.2@deepinfra: 62.3 +/- 3.4, $0.81 qwen3.6-27b@deepinfra: 53.2 +/- 3.5, $0.90 glm-5.3@deepinfra: 69.3 +/- 3.3, $0.95 qwen3.8-27b: 72.7 +/- 3.2, $1.00 qwen3.6-plus: 58.3 +/- 3.5, $1.00 qwen3.6-27b: 53.2 +/- 3.5, $1.20 kimi-k2.6: 64.4 +/- 3.4, $1.30 gemini-3.8-flash: 81.4 +/- 2.8, $1.35 gemini-3.7-flash: 79.9 +/- 2.8, $1.35 gemini-3.5-flash: 75.6 +/- 3.0, $1.35 gemini-3.6-flash: 75.4 +/- 3.1, $1.35 gpt-5.4-mini: 59.8 +/- 3.5, $1.50 deepseek-v4-pro-0813@deepinfra: 67.7 +/- 3.3, $1.56 deepseek-v4-pro@deepinfra: 62.4 +/- 3.4, $1.56 kimi-k2.7-code: 56.3 +/- 3.5, $1.56 inkling: 70.1 +/- 3.2, $1.61 deepseek-v4-pro-0813: 67.7 +/- 3.3, $1.85 deepseek-v4-pro: 62.4 +/- 3.4, $1.85 deepseek-v4-pro@parasail: 62.4 +/- 3.4, $1.85 deepseek-v4-pro@together: 62.4 +/- 3.4, $1.85 glm-5.3: 69.3 +/- 3.3, $2.00 glm-5.3@alibaba-intl: 69.3 +/- 3.3, $2.00 glm-5.3@parasail: 69.3 +/- 3.3, $2.00 glm-5.2: 62.3 +/- 3.4, $2.00 glm-5.2@alibaba-intl: 62.3 +/- 3.4, $2.00 glm-5.2@alibaba-us: 62.3 +/- 3.4, $2.00 deepseek-v4-pro-fast@parasail: 62.4 +/- 3.4, $2.77 qwen3.8-max-0902: 74.1 +/- 3.1, $2.80 glm-5.3-fast@parasail: 69.3 +/- 3.3, $3.00 grok-4.7: 75.3 +/- 3.1, $3.08 grok-4.6: 71.9 +/- 3.2, $3.08 qwen3.7-max: 74.0 +/- 3.1, $3.50 qwen3.7-max@alibaba-us: 74.0 +/- 3.1, $3.50 gpt-6.1-sol: 74.2 +/- 3.1, $3.60 gpt-6-sol: 68.6 +/- 3.3, $3.60 claude-sonnet-5: 63.9 +/- 3.4, $3.60 claude-sonnet-5-5: 56.8 +/- 3.5, $3.60 gemini-3.1-pro-preview: 79.1 +/- 2.9, $4.00 gpt-5.6-terra: 64.6 +/- 3.4, $4.00 gpt-5.2: 61.8 +/- 3.4, $4.20 gpt-5.4: 70.2 +/- 3.2, $5.00 kimi-k3@deepinfra: 71.4 +/- 3.2, $5.13 kimi-k3: 71.4 +/- 3.2, $5.40 kimi-k3@moonshot: 71.4 +/- 3.2, $5.40 claude-sonnet-4-6: 63.2 +/- 3.4, $5.40 gpt-5.6-sol: 71.9 +/- 3.2, $7.20 claude-opus-5-5: 65.7 +/- 3.4, $7.20 claude-opus-4-8: 72.0 +/- 3.2, $9.00 claude-opus-4-7: 66.7 +/- 3.3, $9.00 claude-opus-5: 63.8 +/- 3.4, $9.00 claude-opus-4-6: 63.3 +/- 3.4, $9.00 claude-opus-4-5: 62.6 +/- 3.4, $9.00 gpt-5.5: 70.7 +/- 3.2, $10.00 claude-fable-5: 75.8 +/- 3.0, $18.00 gpt-6-astra: 75.6 +/- 3.0, $18.00 claude-fable-5-1: 73.0 +/- 3.1, $18.00 deepseek-v4-flash-vision-expgemini-3.8-flash Best, Balanced, Cheap
Math, Hard
0255075100$1$10$100 phi-4: 64.9 +/- 1.1, $0.27 deepseek-v4-flash-0731@deepinfra: 86.8 +/- 1.7, $0.28 gemma-3-27b-it: 74.0 +/- 1.1, $0.30 deepseek-v4-flash@deepinfra: 79.7 +/- 2.1, $0.34 gpt-5-nano: 94.9 +/- 0.5, $0.46 llama-4-scout-17b-16e-instruct: 62.3 +/- 1.2, $0.47 llama-3.3-70b-instruct-turbo@deepinfra: 41.6 +/- 1.2, $0.49 deepseek-v4-flash-0731: 86.8 +/- 1.7, $0.53 deepseek-v4-flash-0731@parasail: 86.8 +/- 1.7, $0.53 deepseek-v4-flash@parasail: 79.7 +/- 2.1, $0.53 gpt-4.1-nano: 70.0 +/- 1.0, $0.56 claude-haiku-5-5: 92.8 +/- 1.3, $0.65 gpt-6-luna: 89.1 +/- 1.6, $0.65 deepseek-flash@deepinfra: 93.3 +/- 1.3, $0.66 glm-5.3-flash: 81.2 +/- 2.0, $0.75 glm-5.3-flash@deepinfra: 81.2 +/- 2.0, $0.75 deepseek-v4-flash: 79.7 +/- 2.1, $0.76 gpt-4o-mini: 52.6 +/- 1.1, $0.84 llama-3.3-70b-instruct-turbo@parasail: 41.6 +/- 1.2, $0.89 deepseek-v4-flash-vision-exp: 87.8 +/- 1.7, $1.01 gpt-5.6-luna: 87.2 +/- 1.7, $1.48 gpt-5.4-nano: 91.0 +/- 1.5, $1.53 minimax-m3@deepinfra: 77.0 +/- 2.2, $1.55 deepseek-flash: 93.3 +/- 1.3, $1.68 deepseek-flash@alibaba-intl: 93.3 +/- 1.3, $1.68 deepseek-flash@parasail: 93.3 +/- 1.3, $1.68 deepseek-flash@together: 93.3 +/- 1.3, $1.68 minimax-m3: 77.0 +/- 2.2, $1.68 minimax-m3@parasail: 77.0 +/- 2.2, $1.68 qwen-plus-2025-01-25: 65.3 +/- 1.1, $1.88 qwen3.8-27b@deepinfra: 86.2 +/- 1.8, $1.99 deepseek-v4-flash-0731@alibaba-intl: 86.8 +/- 1.7, $2.07 gpt-4.1-mini: 87.3 +/- 0.7, $2.24 gpt-5-mini: 97.9 +/- 0.3, $2.30 gpt-3.5-turbo: 11.6 +/- 0.6, $2.35 qwen3.8-27b@parasail: 86.2 +/- 1.8, $2.46 deepseek-flash-fast@parasail: 93.3 +/- 1.3, $2.52 minimax-m3-fast@parasail: 77.0 +/- 2.2, $2.52 glm-5.2@deepinfra: 89.8 +/- 1.6, $2.75 gemini-3.5-flash-lite: 73.7 +/- 2.3, $2.85 deepseek-r1-0528: 96.6 +/- 0.4, $2.94 llama-3.3-70b-instruct-turbo: 41.6 +/- 1.2, $3.02 glm-5.3@deepinfra: 87.9 +/- 1.7, $3.38 qwen3.6-27b@deepinfra: 79.9 +/- 2.1, $3.52 qwen3.8-27b: 86.2 +/- 1.8, $3.70 qwen3.6-plus: 83.7 +/- 1.9, $3.70 qwen3.6-27b: 79.9 +/- 2.1, $4.44 kimi-k2.6: 84.3 +/- 1.9, $4.65 gemini-3.7-flash: 93.5 +/- 1.3, $4.88 gemini-3.8-flash: 91.6 +/- 1.4, $4.88 gemini-3.5-flash: 88.2 +/- 1.7, $4.88 gemini-3.6-flash: 86.4 +/- 1.8, $4.88 deepseek-v4-pro-0813@deepinfra: 95.1 +/- 1.1, $4.94 deepseek-v4-pro@deepinfra: 90.7 +/- 1.5, $4.94 kimi-k2.7-code: 79.6 +/- 2.1, $5.50 gpt-5.4-mini: 78.5 +/- 2.1, $5.55 inkling: 88.4 +/- 1.7, $5.65 o4-mini: 97.8 +/- 0.3, $6.16 o3-mini: 96.5 +/- 0.4, $6.16 deepseek-v4-pro-0813: 95.1 +/- 1.1, $6.20 deepseek-v4-pro: 90.7 +/- 1.5, $6.20 deepseek-v4-pro@parasail: 90.7 +/- 1.5, $6.20 deepseek-v4-pro@together: 90.7 +/- 1.5, $6.20 claude-haiku-4-5: 86.9 +/- 0.8, $6.50 glm-5.2: 89.8 +/- 1.6, $6.76 glm-5.2@alibaba-intl: 89.8 +/- 1.6, $6.76 glm-5.2@alibaba-us: 89.8 +/- 1.6, $6.76 glm-5.3: 87.9 +/- 1.7, $6.76 glm-5.3@alibaba-intl: 87.9 +/- 1.7, $6.76 glm-5.3@parasail: 87.9 +/- 1.7, $6.76 deepseek-v4-pro-fast@parasail: 90.7 +/- 1.5, $9.31 qwen3.8-max-0902: 91.3 +/- 1.5, $9.40 glm-5.3-fast@parasail: 87.9 +/- 1.7, $10.14 grok-4.7: 95.7 +/- 1.0, $10.34 grok-4.6: 92.6 +/- 1.4, $10.34 o3: 97.8 +/- 0.3, $11.20 gpt-4.1: 83.0 +/- 0.9, $11.20 gpt-5: 98.1 +/- 0.3, $11.50 qwen3.7-max: 85.3 +/- 1.8, $11.75 qwen3.7-max@alibaba-us: 85.3 +/- 1.8, $11.75 gpt-6.1-sol: 96.8 +/- 0.9, $13.00 gpt-6-sol: 96.4 +/- 1.0, $13.00 claude-sonnet-5-5: 96.1 +/- 1.0, $13.00 claude-sonnet-5: 92.9 +/- 1.3, $13.00 gpt-4o: 49.8 +/- 1.1, $14.00 gpt-5.6-terra: 94.9 +/- 1.1, $14.80 gemini-3.1-pro-preview: 91.0 +/- 1.5, $14.80 gpt-5.2: 93.2 +/- 1.3, $16.10 gpt-5.4: 94.2 +/- 1.2, $18.50 kimi-k3@deepinfra: 84.4 +/- 1.9, $18.53 claude-sonnet-4-5: 97.7 +/- 0.4, $19.50 claude-sonnet-4-6: 87.0 +/- 1.7, $19.50 kimi-k3: 84.4 +/- 1.9, $19.50 kimi-k3@moonshot: 84.4 +/- 1.9, $19.50 claude-opus-5-5: 97.1 +/- 0.9, $26.00 gpt-5.6-sol: 96.2 +/- 1.0, $26.00 claude-opus-5: 95.7 +/- 1.0, $32.50 claude-opus-4-8: 94.3 +/- 1.2, $32.50 claude-opus-4-7: 92.9 +/- 1.3, $32.50 claude-opus-4-5: 90.4 +/- 1.5, $32.50 claude-opus-4-6: 89.3 +/- 1.6, $32.50 gpt-5.5: 95.9 +/- 1.0, $37.00 gpt-4-turbo: 46.7 +/- 1.1, $47.00 claude-fable-5-1: 97.0 +/- 0.9, $65.00 gpt-6-astra: 96.8 +/- 0.9, $65.00 claude-fable-5: 96.0 +/- 1.0, $65.00 o1: 81.7 +/- 1.1, $84.00 gpt-4: 23.0 +/- 0.9, $114 deepseek-v4-flash-vision-expgpt-5-mini Best, Balanced, Cheap

Sources

What these numbers are

  • These numbers come from the sources named on each row, not from Zabio's own tests. Zabio's tests are shown separately and never combined with them into one figure.
  • Sources test models at their own settings. A settings mismatch against how Zabio calls the model is marked on the row and lowers its weight.
  • Scores are compared only inside one benchmark. Task scores combine benchmarks by evidence in standard errors, so a task score is a summary, not a benchmark result.
  • A model missing from every source is listed as such rather than left out.

Results from our own tests have their own section.

Models with no public results yet

These models are in the catalog, and no source we read publishes a result for them.

  • mistral-small-2603
  • codestral-2508
  • chat-latest
  • ministral-3b-2512
  • ministral-8b-2512
  • ministral-14b-2512
  • qwen3.8-2.4t-a95b
  • muse-glimmer-30b
  • qwen3.8-omni-flash
  • qwen3.8-flash
  • qwen3.8-2.4t-a95b@alibaba-intl
  • qwen3.5-plus-2026-04-20
  • qwen3.5-plus-2026-02-15
  • kimi-k3.1-pro-highspeed
  • ling-3.0-flash
  • ling-3.0-flash-vl
  • ling-3.1-flash
  • llama-guard-4-12b
  • muse-glimmer-30b@deepinfra
  • mistral-small-3.2-24b-instruct-2506
  • qwen3-vl-30b-a3b-instruct
  • gpt-audio-1.5
  • gpt-audio
  • gpt-audio-mini
  • ripple-65b-preview
  • glm-5.3-prime

Where to next

News

How routing picks between these models

Model and company names are trademarks of their owners. Zabio uses these models through their vendors' APIs and is not affiliated with the vendors.