GPT-5.3-Codex vs Ministral 3 8B 2512
GPT-5.3-Codex leads Ministral 3 8B 2512 on the Artificial Analysis Intelligence Index, 32.5 to 5.5, and Ministral 3 8B 2512 costs 93.3x less per output token ($0.15 vs $14.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
GPT-5.3-Codex or Ministral 3 8B 2512: which to pick
Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Ministral 3 8B 2512 has none, so the two cannot be ranked on coding.
Pick Ministral 3 8B 2512 for output tokens 93.3x cheaper ($0.15 vs $14.00 per million) and work measured by Design Arena: 3D, where it leads.
- Shared results
- 5
- GPT-5.3-Codex only
- 29
- Ministral 3 8B 2512 only
- 2
- 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 5.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Ministral 3 8B 2512 has a AA Agentic Index result, 0.6.
Directional only
Web design
Design Arena: websites
GPT-5.3-Codex
GPT-5.3-Codex leads, 1162 against 1065.
Same board, both measured
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
Ministral 3 8B 2512
GPT-5.3-Codex $0.0088, Ministral 3 8B 2512 $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.3-Codex has the number, $0.59.
Directional only
At a glance
- Coding index
- GPT-5.3-Codex 60.0 from 3 benchmarks, Ministral 3 8B 2512 not benchmarked.
- Widest category
- Intelligence, 27.0 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: GPT-5.3-Codex 32.5 against Ministral 3 8B 2512 5.5, 27.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5.3-Codex $14.00 against Ministral 3 8B 2512 $0.15 per million output tokens, 93.3x apart.
- Context window
- GPT-5.3-Codex takes 400K tokens, Ministral 3 8B 2512 262K.
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 | GPT-5.3-Codex | Bars | Ministral 3 8B 2512 | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Web design | 3 | 1 | ||
| All shared boards | 4 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index13 boards, none shared
| Benchmark | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| LMArena WebDev | 1407 | Not measured | Only GPT-5.3-Codex measured |
| AA Coding Index | Not measured | 9.7 | Only Ministral 3 8B 2512 measured |
| LiveCodeBench (Vals AI) | 87.3% | Not measured | Only GPT-5.3-Codex measured |
| SWE-bench Verified (Vals AI) | 78.0% | Not measured | Only GPT-5.3-Codex measured |
| Vibe Code Bench (Vals AI) | 61.8% | Not measured | Only GPT-5.3-Codex measured |
| IOI (Vals AI) | 53.8% | Not measured | Only GPT-5.3-Codex measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.0% | Not measured | Only GPT-5.3-Codex measured |
| Terminal-Bench | 78.4% | Not measured | Only GPT-5.3-Codex measured |
| WeirdML | 79.3% | Not measured | Only GPT-5.3-Codex measured |
| ALE-Bench | 1655.2 | Not measured | Only GPT-5.3-Codex measured |
| LMArena WebDev: React | 1395 | Not measured | Only GPT-5.3-Codex measured |
| LMArena WebDev: HTML | 1422 | Not measured | Only GPT-5.3-Codex measured |
| LMArena WebDev: from an image | 1443 | Not measured | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 32.5 | 5.5 | GPT-5.3-Codex |
| Epoch Capabilities Index | 157.1 | Not measured | Only GPT-5.3-Codex measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.6 | Only Ministral 3 8B 2512 measured |
| Design Arena: agents building web apps | 1032 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building full-stack apps | 983 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building mobile apps | 1053 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building Android apps | 1084 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: agents building Godot games | 1124 | Not measured | Only GPT-5.3-Codex measured |
| τ²-Bench Telecom | 86.0% | Not measured | Only GPT-5.3-Codex measured |
| METR time horizons | 74.5% | Not measured | Only GPT-5.3-Codex measured |
| Vending-Bench 2 | $5,940 | Not measured | 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 | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 91.5% | Not measured | Only GPT-5.3-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | 42.5% | Not measured | 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 | GPT-5.3-Codex | Ministral 3 8B 2512 | 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 | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| Neither model has a result on 18 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | 1162 | 1065 | GPT-5.3-Codex |
| Design Arena: UI components | 1134 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: game dev | 1161 | 990 | GPT-5.3-Codex |
| Design Arena: data viz | 1164 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: 3D | 1007 | 1031 | Ministral 3 8B 2512 |
| Design Arena: all code categories | 1144 | 1053 | GPT-5.3-Codex |
| Design Arena: SVG | 1129 | Not measured | Only GPT-5.3-Codex measured |
| Design Arena: ASCII art | 1152 | Not measured | 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 | GPT-5.3-Codex | Ministral 3 8B 2512 | Leader |
|---|---|---|---|
| IFBench | 75.4% | Not measured | Only GPT-5.3-Codex measured |
| Long context reasoning (AA-LCR) | 83.3% | Not measured | 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 | GPT-5.3-Codex | Ministral 3 8B 2512 | 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
Ministral 3 8B 2512 costs less
Repository review
50K input + 3K output tokens
Ministral 3 8B 2512 costs less
Agent loop
200K input + 10K output tokens
Ministral 3 8B 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 | OpenAI GPT-5.3-Codex | Mistral Ministral 3 8B 2512 |
|---|---|---|
| Maker | OpenAI | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | February 24, 2026 | December 2, 2025 |
| Context window | 400K | 262K |
| Input $/Mtok | $1.75 | $0.15 |
| Output $/Mtok | $14.00 | $0.15 |
| Coding index | 60.0 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.59 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.3-Codex better than Ministral 3 8B 2512 for coding?
Only GPT-5.3-Codex has a coding score, 60.0 on the Vibe Coding Index; Ministral 3 8B 2512 has none, so the two cannot be ranked on coding. Pick Ministral 3 8B 2512 for output tokens 93.3x cheaper ($0.15 vs $14.00 per million) and work measured by Design Arena: 3D, where it leads.
Which is cheaper, GPT-5.3-Codex or Ministral 3 8B 2512?
GPT-5.3-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Ministral 3 8B 2512 costs $0.15 and $0.15. Cost per solved task is known for GPT-5.3-Codex only.
Which has the bigger context window, GPT-5.3-Codex or Ministral 3 8B 2512?
GPT-5.3-Codex, with 400K tokens against 262K.
How many benchmarks is the GPT-5.3-Codex vs Ministral 3 8B 2512 comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. GPT-5.3-Codex's coding index rests on 3 independent benchmarks and Ministral 3 8B 2512's on 0. Where only one model has a result, the page says so instead of naming a winner.