GPT-5-Codex vs Gemini 2.5 Computer Use Preview vs Jamba Large

GPT-5-Codex is the better all-round choice, scoring 42/100 against Gemini 2.5 Computer Use Preview (35) and Jamba Large (30). It leads on inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

GPT-5-Codex is cheaper at $1.25 input / $10.00 output per million tokens (median across 3 API providers). Gemini 2.5 Computer Use Preview costs $1.25 input / $10.00 output per million tokens (official Google API price); Jamba Large costs $2.00 input / $8.00 output per million tokens (official AI21 Labs API price). At a typical mix of three input tokens to one output token, that is $3.44 per million tokens for GPT-5-Codex versus $3.44 for Gemini 2.5 Computer Use Preview (1× as much) and $3.50 for Jamba Large (1× as much).

There is no independent benchmark that covers all three models yet. GPT-5-Codex has not been scored yet, Gemini 2.5 Computer Use Preview has not been scored yet and Jamba Large has not been scored yet.

There are no published SWE-bench Verified results for GPT-5-Codex, Gemini 2.5 Computer Use Preview and Jamba Large yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

GPT-5-Codex has the largest context window at 400,000 tokens, against 256,000 for Jamba Large and 128,000 for Gemini 2.5 Computer Use Preview. Maximum output per response: GPT-5-Codex up to 128,000, Gemini 2.5 Computer Use Preview up to 64,000, Jamba Large up to 4,096 tokens.

GPT-5-Codex accepts text and images; Gemini 2.5 Computer Use Preview accepts text and images; Jamba Large accepts text. GPT-5-Codex handles the widest range of inputs.

Jamba Large publishes its weights and can be self-hosted; GPT-5-Codex and Gemini 2.5 Computer Use Preview is proprietary.

Gemini 2.5 Computer Use Preview is the newest, released Oct 7, 2025. GPT-5-Codex came out Sep 15, 2025; Jamba Large came out Jul 1, 2025. Knowledge cutoff: GPT-5-Codex Sep 30, 2024, Gemini 2.5 Computer Use Preview Jan 2025, Jamba Large Aug 22, 2024.

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.