GPT-3.5 Turbo Instruct vs GPT-5.2-Codex
GPT-3.5 Turbo Instruct costs 7.0x less per output token than GPT-5.2-Codex ($2.00 vs $14.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $2.00
- Coding
- 45.4
- Overall
- No data
- Output $/M
- $14.00
GPT-3.5 Turbo Instruct or GPT-5.2-Codex: which to pick
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; GPT-3.5 Turbo Instruct has none, so the two cannot be ranked on coding.
Pick GPT-3.5 Turbo Instruct for output tokens 7.0x cheaper ($2.00 vs $14.00 per million).
No benchmark has tested both yet. GPT-3.5 Turbo Instruct has results on METR time horizons; GPT-5.2-Codex on SWE-bench Verified, SWE-bench Multilingual and LMArena WebDev. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GPT-5.2-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only GPT-5.2-Codex has a AA Intelligence Index result, 28.5.
Directional only
Long documents
Listed context window
GPT-5.2-Codex
GPT-5.2-Codex takes 400K tokens against 4K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-3.5 Turbo Instruct
GPT-3.5 Turbo Instruct $0.0025, GPT-5.2-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2-Codex has the number, $0.43.
Directional only
At a glance
- Coding index
- GPT-3.5 Turbo Instruct not benchmarked, GPT-5.2-Codex 45.4 from 3 benchmarks.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GPT-3.5 Turbo Instruct $2.00 against GPT-5.2-Codex $14.00 per million output tokens, 7.0x apart.
- Context window
- GPT-3.5 Turbo Instruct takes 4K tokens, GPT-5.2-Codex 400K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index11 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | GPT-5.2-Codex | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 72.8% | Only GPT-5.2-Codex measured |
| SWE-bench Multilingual | Not measured | 66.3% | Only GPT-5.2-Codex measured |
| LMArena WebDev | Not measured | 1339 | Only GPT-5.2-Codex measured |
| LiveCodeBench (Vals AI) | Not measured | 88.0% | Only GPT-5.2-Codex measured |
| SWE-bench Verified (Vals AI) | Not measured | 72.4% | Only GPT-5.2-Codex measured |
| Vibe Code Bench (Vals AI) | Not measured | 37.9% | Only GPT-5.2-Codex measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 37.1% | Only GPT-5.2-Codex measured |
| Terminal-Bench | Not measured | 66.5% | Only GPT-5.2-Codex measured |
| ALE-Bench | Not measured | 1299.9 | Only GPT-5.2-Codex measured |
| LMArena WebDev: React | Not measured | 1329 | Only GPT-5.2-Codex measured |
| LMArena WebDev: HTML | Not measured | 1348 | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GPT-3.5 Turbo Instruct | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 28.5 | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1051 | Only GPT-5.2-Codex measured |
| Design Arena: agents building full-stack apps | Not measured | 993 | Only GPT-5.2-Codex measured |
| Design Arena: agents building mobile apps | Not measured | 1090 | Only GPT-5.2-Codex measured |
| Design Arena: agents building Android apps | Not measured | 1176 | Only GPT-5.2-Codex measured |
| Design Arena: agents building Godot games | Not measured | 1142 | Only GPT-5.2-Codex measured |
| τ²-Bench Telecom | Not measured | 92.1% | Only GPT-5.2-Codex measured |
| METR time horizons | 21.5% | Not measured | Only GPT-3.5 Turbo Instruct measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | GPT-5.2-Codex | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.9% | Only GPT-5.2-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 35.7% | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 20 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | GPT-5.2-Codex | Leader |
|---|---|---|---|
| IFBench | Not measured | 77.6% | Only GPT-5.2-Codex measured |
| Long context reasoning (AA-LCR) | Not measured | 82.3% | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 44 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GPT-3.5 Turbo Instruct costs less
Repository review
50K input + 3K output tokens
GPT-3.5 Turbo Instruct costs less
Agent loop
200K input + 10K output tokens
GPT-3.5 Turbo Instruct costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-3.5 Turbo Instruct | OpenAI GPT-5.2-Codex |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | September 28, 2023 | January 14, 2026 |
| Context window | 4K | 400K |
| Input $/Mtok | $1.50 | $1.75 |
| Output $/Mtok | $2.00 | $14.00 |
| Coding index | Not benchmarked | 45.4 |
| Independent measurements behind it | 0 | 3 |
| Cost per solved task | Not computable | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-3.5 Turbo Instruct better than GPT-5.2-Codex for coding?
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; GPT-3.5 Turbo Instruct has none, so the two cannot be ranked on coding. Pick GPT-3.5 Turbo Instruct for output tokens 7.0x cheaper ($2.00 vs $14.00 per million).
Which is cheaper, GPT-3.5 Turbo Instruct or GPT-5.2-Codex?
GPT-3.5 Turbo Instruct costs $1.50 per million input tokens and $2.00 per million output tokens; GPT-5.2-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.2-Codex only.
Which has the bigger context window, GPT-3.5 Turbo Instruct or GPT-5.2-Codex?
GPT-5.2-Codex, with 400K tokens against 4K.
Has any benchmark tested both GPT-3.5 Turbo Instruct and GPT-5.2-Codex?
No benchmark has tested both yet. GPT-3.5 Turbo Instruct has results on METR time horizons; GPT-5.2-Codex on SWE-bench Verified, SWE-bench Multilingual and LMArena WebDev. Compare them on price and context instead. Data as of October 21, 2026.