Across 7 comparable benchmarks, Gemini 3.5 Flash has better reported results on 7 and worse on 0.
Moderate evidence7 of 7 shared results countedHow we compare
GPT-5.2-Codex is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | GPT-5.2-Codex | Gemini 3.5 Flash |
|---|---|---|
| Context window | — | 1M tokens |
| Input / 1M | — | $1.50 |
| Output / 1M | — | $9.00 |
| Blended (4:1) | — | $2.03 |
| Status | Retired | Deprecated |
| Released | December 18, 2025 | May 19, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 5 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 3.5 Flash ahead on 4 of 4 counted
Gemini 3.5 Flash ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Gemini 3.5 Flash ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Mathematics, Computer & tool use, Research & search, Long context, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT-5.2-Codex relative to Gemini 3.5 Flash. Reading the results
| Benchmark | GPT-5.2-Codex | Gemini 3.5 Flash | Gap |
|---|---|---|---|
| APEX-SWERepository Engineering · Pass@1 | 30.8Thinking High · tools | 36.1Thinking High · tools | −5.3 pts#51 vs #41 of 61 |
| SWE-Bench Pro - PublicRepository Engineering · Accuracy | 41.0Unspecified Reasoning · tools | 55.1≠Thinking High · tools | −14.1 pts#60 vs #34 of 66 |
| Terminal Bench HardAgentic Development · Accuracy | 37.1Extra-High · tools | 46.2≠Normal · tools | −9.1 pts#43 vs #18 of 157 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 37.9Thinking High · tools | 48.7Thinking High · tools | −10.8 pts#73 vs #65 of 121 |
| CritPtScientific Reasoning · Score | 8.7Extra-High · no tools | 13.1≠Thinking High · no tools | 0.66×#60 vs #46 of 134 |
| MMMU-ProVisual Understanding · Accuracy | 76.3Extra-High · no tools | 84.3≠Thinking High · no tools | −8.0 pts#58 vs #11 of 136 |
| LiveBenchCross-capability Suites · Accuracy | 74.0Normal · no tools | 74.6≠Thinking High · no tools | −0.7 pts#39 vs #35 of 106 |
Repository Engineering · Pass@1
Repository Engineering · Accuracy
Agentic Development · Accuracy
Code Generation & Editing · Pass rate (%)
Scientific Reasoning · Score
Visual Understanding · Accuracy
Cross-capability Suites · Accuracy
A dash means no result is available.
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
GPT-5.2-Codex: Listed text rates; pricing tier not confirmed.
Gemini 3.5 Flash: Standard pricing. Official Gemini Developer API standard input price. Official Gemini Developer API output price, including thinking tokens.
| Price / 1M tokens | GPT-5.2-Codex | Gemini 3.5 Flash | Ratio |
|---|---|---|---|
| Input | — | $1.50 | — |
| Output | — | $9.00 | — |
| Cached input | — | $0.15 | — |
| Cache write | — | — | — |
| Blended | — | $2.03 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | GPT-5.2-Codex | Gemini 3.5 Flash |
|---|---|---|
| AIME 2026 | Not reported | |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | $0.8503 / task Average · ARC-AGI-2 Score: 72.1 Thinking High (With Tools) |
| AutomationBench | Not reported | $0.42 / task Average · Pass Rate: 13.4 Thinking High (With Tools) · zapier-private-heldout $0.38 / task Average · Pass Rate: 11.4 Thinking Medium (With Tools) · zapier-private-heldout 1 more settings |
| DeepSWE | Not reported | |
| Tax Agent Bench | Not reported | $0.8597 / task Average · Accuracy (%, rubric × citation quality): 21.6 Thinking High (With Tools) |
| Terminal-Bench 4.0 | Not reported | $5.98 / task Average · Resolution rate (%): 6.1 Unspecified Reasoning (With Tools) · vals-mini-swe |
| Vals Index v2.1 | Not reported |
| Attribute | GPT-5.2-Codex | Gemini 3.5 Flash |
|---|---|---|
| Availability | Retired | Deprecated |
| Provider | OpenAI | Google Deep Mind |
| Model type | Coding model | Multimodal model |
| First release | December 18, 2025 | May 19, 2026 |
| Context window | — | 1M tokens |
| Max output | — | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Coding | Reasoning, Multilingual, Function calling, Tool use, Structured output, Web search, Computer use, Long context |
| Knowledge cutoff | — | 2025-01 |
| Input modalities | Text, Image | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used GPT-5.2-Codex or Gemini 3.5 Flash? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.