GPT-6.1 Terra vs Gemini 4 Argon: benchmarks and token cost

This comparison uses GPT-6.1 Terra (Max) and Gemini 4 Argon (High). It reports the captured benchmark data, with no new hands-on test.

A close overall index with a large rate difference

Terra records 51.0 on the captured intelligence index and Argon 50.4. Terra’s listed input and output token rates are one quarter of Argon’s. The small aggregate gap does not establish a specialized advantage, but the rate difference is useful for a cost-controlled trial. Confirm equivalent request settings and compare accepted answers rather than raw token volume.

How to read the table

The intelligence index is an aggregate measurement, not a percentage of correct answers in your application. Input and output prices are separate rates per million tokens. Coding and math indices are unavailable in this capture and must not be read as zero. Compare first-token latency separately from output-token throughput, and use the same model effort settings for a trial. Choose using task quality, total time and the cost of accepted results; provider features and deployment requirements need their own checks.