Devstral 2 2512 vs GPT-5.3-Codex
GPT-5.3-Codex leads Devstral 2 2512 on the Artificial Analysis Intelligence Index, 32.5 to 8.6, and Devstral 2 2512 costs 7.0x less per output token ($2.00 vs $14.00 per million). Updated October 22, 2026; 3 benchmarks have a result for both.
Devstral 2 2512 or GPT-5.3-Codex: which to pick
Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding.
Pick Devstral 2 2512 for output tokens 7.0x cheaper ($2.00 vs $14.00 per million).
- Shared results
- 3
- Devstral 2 2512 only
- 3
- GPT-5.3-Codex only
- 31
- Like-for-like categories
- 2 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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-5.3-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.3-Codex
GPT-5.3-Codex leads, 32.5 against 8.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Devstral 2 2512 has a AA Agentic Index result, 2.3.
Directional only
Web design
Design Arena: websites
No call
Only GPT-5.3-Codex has a Design Arena: websites result, 1162.
Directional only
Long documents
Listed context window
GPT-5.3-Codex
GPT-5.3-Codex takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Devstral 2 2512
Devstral 2 2512 $0.0014, GPT-5.3-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.3-Codex
Devstral 2 2512 $1.19, GPT-5.3-Codex $0.59.
Published attempt cost and pass rate
At a glance
- Coding index
- Devstral 2 2512 not benchmarked, GPT-5.3-Codex 60.0 from 3 benchmarks.
- Widest category
- Coding, 25.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- LiveCodeBench (Vals AI): Devstral 2 2512 51.8% against GPT-5.3-Codex 87.3%, 35.5 points apart on a 0 to 100 scale.
- Output price
- Devstral 2 2512 $2.00 against GPT-5.3-Codex $14.00 per million output tokens, 7.0x apart.
- Context window
- Devstral 2 2512 takes 262K tokens, GPT-5.3-Codex 400K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Devstral 2 2512 | Bars | GPT-5.3-Codex | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| SWE-bench Verified | 53.8% | Not measured | Only Devstral 2 2512 measured |
| LMArena WebDev | Not measured | 1407 | Only GPT-5.3-Codex measured |
| AA Coding Index | 31.3 | Not measured | Only Devstral 2 2512 measured |
| LiveCodeBench (Vals AI) | 51.8% | 87.3% | GPT-5.3-Codex |
| SWE-bench Verified (Vals AI) | 62.8% | 78.0% | GPT-5.3-Codex |
| Vibe Code Bench (Vals AI) | Not measured | 61.8% | Only GPT-5.3-Codex measured |
| IOI (Vals AI) | Not measured | 53.8% | Only GPT-5.3-Codex measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 53.0% | Only GPT-5.3-Codex measured |
| Terminal-Bench | Not measured | 78.4% | Only GPT-5.3-Codex measured |
| WeirdML | Not measured | 79.3% | Only GPT-5.3-Codex measured |
| ALE-Bench | Not measured | 1655.2 | Only GPT-5.3-Codex measured |
| LMArena WebDev: React | Not measured | 1395 | Only GPT-5.3-Codex measured |
| LMArena WebDev: HTML | Not measured | 1422 | Only GPT-5.3-Codex measured |
| LMArena WebDev: from an image | Not measured | 1443 | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 8.6 | 32.5 | GPT-5.3-Codex |
| Epoch Capabilities Index | Not measured | 157.1 | Only GPT-5.3-Codex measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| AA Agentic Index | 2.3 | Not measured | Only Devstral 2 2512 measured |
| Design Arena: agents building web apps | Not measured | 1032 | Only GPT-5.3-Codex measured |
| Design Arena: agents building full-stack apps | Not measured | 983 | Only GPT-5.3-Codex measured |
| Design Arena: agents building mobile apps | Not measured | 1053 | Only GPT-5.3-Codex measured |
| Design Arena: agents building Android apps | Not measured | 1084 | Only GPT-5.3-Codex measured |
| Design Arena: agents building Godot games | Not measured | 1124 | Only GPT-5.3-Codex measured |
| τ²-Bench Telecom | Not measured | 86.0% | Only GPT-5.3-Codex measured |
| METR time horizons | Not measured | 74.5% | Only GPT-5.3-Codex measured |
| Vending-Bench 2 | Not measured | $5,940 | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 32 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.5% | Only GPT-5.3-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 42.5% | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 20 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Neither model has a result on 18 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1162 | Only GPT-5.3-Codex measured |
| Design Arena: UI components | Not measured | 1134 | Only GPT-5.3-Codex measured |
| Design Arena: game dev | Not measured | 1161 | Only GPT-5.3-Codex measured |
| Design Arena: data viz | Not measured | 1164 | Only GPT-5.3-Codex measured |
| Design Arena: 3D | Not measured | 1007 | Only GPT-5.3-Codex measured |
| Design Arena: all code categories | Not measured | 1144 | Only GPT-5.3-Codex measured |
| Design Arena: SVG | Not measured | 1129 | Only GPT-5.3-Codex measured |
| Design Arena: ASCII art | Not measured | 1152 | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| IFBench | Not measured | 75.4% | Only GPT-5.3-Codex measured |
| Long context reasoning (AA-LCR) | Not measured | 83.3% | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 44 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Devstral 2 2512 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Neither model has a result on 5 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
Devstral 2 2512 costs less
Repository review
50K input + 3K output tokens
Devstral 2 2512 costs less
Agent loop
200K input + 10K output tokens
Devstral 2 2512 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 | Mistral Devstral 2 2512 | OpenAI GPT-5.3-Codex |
|---|---|---|
| Maker | Mistral AI | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | December 9, 2025 | February 24, 2026 |
| Context window | 262K | 400K |
| Input $/Mtok | $0.40 | $1.75 |
| Output $/Mtok | $2.00 | $14.00 |
| Coding index | Not benchmarked | 60.0 |
| Independent measurements behind it | 1 | 3 |
| Cost per solved task | $1.19 | $0.59 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Devstral 2 2512 better than GPT-5.3-Codex for coding?
Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding. Pick Devstral 2 2512 for output tokens 7.0x cheaper ($2.00 vs $14.00 per million).
Which is cheaper, Devstral 2 2512 or GPT-5.3-Codex?
Devstral 2 2512 costs $0.40 per million input tokens and $2.00 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Per solved SWE-bench Verified task, Devstral 2 2512 costs $1.19 and GPT-5.3-Codex $0.59.
Which has the bigger context window, Devstral 2 2512 or GPT-5.3-Codex?
GPT-5.3-Codex, with 400K tokens against 262K.
How many benchmarks is the Devstral 2 2512 vs GPT-5.3-Codex comparison based on?
3 benchmarks have a result for both models as of October 22, 2026. Devstral 2 2512's coding index rests on 1 independent benchmark and GPT-5.3-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.