Gemini 3 Pro Preview
- Input price
- —
- Per 1 million tokens (USD)
- Output price
- —
- Per 1 million tokens (USD)
- Effort levels
- 2total
- Default: High
- Benchmark results
- 4total
- Benchmark types: 4
Model information
- API model ID
- gemini-3-pro-preview
- release date
- Unknown
- effort
- Low / High (default)
- Effort source
- Based on the row "gemini-3-pro-preview | On (high) | low, high" in the table in Gemini API thinking documentation (aistudio.google.com/docs/thinking, retrieved 2026-11-13). Discontinued ("Gemini 3 Pro Preview is deprecated and was shut down on March 9, 2026" on the model page).
- Claude Code
- unknown
- Codex
- unknown
- Availability notes
- Not collected (the official model list for Claude Code and the one for Codex were not checked this time).
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | — |
|---|---|
| output | — |
| cache read | — |
| cache write | — |
Not collected.
Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| τ²-bench airline (v1.0.1)High (default) | High | 80.5% | — | Sierra | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Google": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Evaluation date 2026-03-02. Notes summary: 4 trial runs; seed not stated; infrastructure errors treated as failures (0 points) (3 cases).transcribed from tableSource excerptairline.pass_1=80.5Location In submissions/gemini-3-pro_sierra_2026-03-02/submission.json: results.airline.pass_1 (line 22 of file). model_name "Gemini 3 Pro". methodology.notes (line 56) |
| τ²-bench banking_knowledge (v1.0.1)High (default) | High | 18.0% | — | Sierra | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Google": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "terminal". Evaluation date 2026-03-02. Notes summary: rescored on 2026-07-15 following a scoring correction in v1.0.1; 4 trial runs; seed not stated; 42 cases terminated due to max_steps and scored 0 points.transcribed from tableSource excerptbanking_knowledge.pass_1=18.04Location In submissions/gemini-3-pro_sierra_2026-03-02/submission.json: results.banking_knowledge.pass_1 (line 43 of file). model_name "Gemini 3 Pro". methodology.notes (line 56) |
| τ²-bench retail (v1.0.1)High (default) | High | 75.9% | — | Sierra | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Google": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Evaluation date 2026-03-02. Notes summary: 4 trial runs; seed not stated; infrastructure errors treated as failures (0 points) (20 cases).transcribed from tableSource excerptretail.pass_1=75.88Location In submissions/gemini-3-pro_sierra_2026-03-02/submission.json: results.retail.pass_1 (line 29 of file). model_name "Gemini 3 Pro". methodology.notes (line 56) |
| τ²-bench telecom (v1.0.1)High (default) | High | 91.0% | — | Sierra | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission gemini-3-pro_sierra_2026-03-02 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Google": Run by Sierra, which operates τ²-bench (third-party measurement). Verified on the leaderboard (trajectories available, prompts not modified, no questions omitted). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Evaluation date 2026-03-02. Notes summary: 4 trial runs; seed not stated; infrastructure errors treated as failures (0 points) (2 cases).transcribed from tableSource excerpttelecom.pass_1=91.01Location In submissions/gemini-3-pro_sierra_2026-03-02/submission.json: results.telecom.pass_1 (line 36 of file). model_name "Gemini 3 Pro". methodology.notes (line 56) |
Related rankings
- Overall ranking (all models, records)
- τ²-bench airline (v1.0.1) ranking by metric (all models, records)
- τ²-bench banking_knowledge (v1.0.1) ranking by metric (all models, records)
- τ²-bench retail (v1.0.1) ranking by metric (all models, records)
- τ²-bench telecom (v1.0.1) ranking by metric (all models, records)
- Recommendations by role