GPT-6.1 Sol leads the current AA Intelligence Index, 55 to 32. DeepSeek V4.1 Flash 1017 costs $0.0042 per illustrated request versus $0.03 for GPT and outputs 178.3 versus 79.3 tokens/s.
AA SciCode: DeepSeek V4.1 Flash 1017 55.90% / GPT-6.1 Sol 54.17%.12
Reasoning benchmark
DeepSeek produces output faster in the current reference deployment: 178.3 tokens/s versus GPT at 79.3 tokens/s.12
Context window (tokens)
GPT lists 1,050,000 context tokens; DeepSeek lists 1,048,576, leaving only a small capacity difference.12
Estimated request cost
At the same billed token quantities, GPT costs $0.03 and DeepSeek $0.0042; DeepSeek leaves more of the request budget available.43
Methodology and sources
SciCode is AA’s scientific-coding evaluation, reported as a percentage; higher is better. It is separate from the 10,000-input-token performance test and is not an in-editor Cline evaluation. Quality and performance use the configurations shown beside the model names. A current AA v5 Intelligence Index is displayed only where both models have a published value. AA performance uses the 10,000-input-token benchmark at each model’s displayed configuration; reasoning settings vary by model. Output speed is the median output rate. Answer latency measures the first answer token after reasoning, not the initial streamed reasoning chunk. For non-streamed reasoning and non-reasoning models, AA reports the same first-chunk and first-answer event. AA estimates answer latency from initial response and reasoning duration; it is not a separately sampled median. These are reference deployments, not Novita endpoint guarantees. The uncached cost example bills 10,000 input and 1,000 output tokens at each named seller’s tariff; it is not the cost of the AA benchmark. Prices, context and output limits use the cited seller sources.4