Enter opens the highlighted result. Esc closes.

Devstral 2 2512 vs GLM 5.3 Flash

GLM 5.3 Flash leads Devstral 2 2512 on the Artificial Analysis Intelligence Index, 41.8 to 8.6, and GLM 5.3 Flash costs 4.0x less per output token ($0.50 vs $2.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.

Replace Devstral 2 2512 Replace GLM 5.3 Flash
Devstral 2 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
0
GLM 5.3 FlashZ.ai
Coding
57.7
Overall
66.0
Output $/M
$0.50
5
vs boards won of 5 shared

Devstral 2 2512 or GLM 5.3 Flash: which to pick

Only GLM 5.3 Flash has a coding score, 57.7 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model ADevstral 2 2512Mistral AINot benchmarked1 independent benchmark$1.19 per solved taskModel BGLM 5.3 FlashZ.ai57.7/1006 independent benchmarks$0.02 per solved task
Shared results
5
Devstral 2 2512 only
1
GLM 5.3 Flash only
97
Like-for-like categories
3 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.

At a glance

Coding index
Devstral 2 2512 not benchmarked, GLM 5.3 Flash 57.7 from 6 benchmarks.
Widest category
Agentic work, 48.6 points apart on average over 1 shared benchmark.
Widest single gap
AA Agentic Index: Devstral 2 2512 2.3 against GLM 5.3 Flash 50.9, 48.6 points apart on a 0 to 100 scale.
Output price
Devstral 2 2512 $2.00 against GLM 5.3 Flash $0.50 per million output tokens, 4.0x apart.
Context window
Devstral 2 2512 takes 262K tokens, GLM 5.3 Flash 1.05M.

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.

Boards won, where both have a result
CategoryDevstral 2 2512BarsGLM 5.3 FlashTies
Coding03
Intelligence01
Agentic work01
All shared boards05
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
SWE-bench Verified53.8%Not measuredOnly Devstral 2 2512 measured
LiveBench codingNot measured80.6%Only GLM 5.3 Flash measured
LMArena WebDevNot measured1607Only GLM 5.3 Flash measured
AA Coding Index31.371.5GLM 5.3 Flash
LiveCodeBench (Vals AI)51.8%80.5%GLM 5.3 Flash
SWE-bench Verified (Vals AI)62.8%92.0%GLM 5.3 Flash
Terminal-Bench 4 (Vals AI)Not measured37.4%Only GLM 5.3 Flash measured
Vibe Code Bench (Vals AI)Not measured30.8%Only GLM 5.3 Flash measured
Code migration (Vals AI)Not measured20.5%Only GLM 5.3 Flash measured
ProgramBench (Vals AI)Not measured0.0%Only GLM 5.3 Flash measured
IOI (Vals AI)Not measured52.5%Only GLM 5.3 Flash measured
Terminal-Bench 2.1 (Vals AI)Not measured62.9%Only GLM 5.3 Flash measured
Vibe Code Bench 1-100 (Vals AI)Not measured16.0%Only GLM 5.3 Flash measured
SkillsBench (Vals AI)Not measured40.2%Only GLM 5.3 Flash measured
CyberBench (Vals AI)Not measured67.9%Only GLM 5.3 Flash measured
SciCodeNot measured51.6%Only GLM 5.3 Flash measured
FrontierCodeNot measured31.8%Only GLM 5.3 Flash measured
FrontierSWENot measured18.1%Only GLM 5.3 Flash measured
ALE-BenchNot measured303.6Only GLM 5.3 Flash measured
LMArena Text: codingNot measured1507Only GLM 5.3 Flash measured
LMArena Text: software and ITNot measured1500Only GLM 5.3 Flash measured
LMArena WebDev: ReactNot measured1624Only GLM 5.3 Flash measured
LMArena WebDev: HTMLNot measured1577Only GLM 5.3 Flash measured
LMArena WebDev: from an imageNot measured1578Only GLM 5.3 Flash measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
AA Intelligence Index8.641.8GLM 5.3 Flash
Epoch Capabilities IndexNot measured153.1Only GLM 5.3 Flash measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
AA Agentic Index2.350.9GLM 5.3 Flash
LiveBench researchNot measured70.1%Only GLM 5.3 Flash measured
LiveBench browserNot measured84.0%Only GLM 5.3 Flash measured
LiveBench long agenticNot measured28.4%Only GLM 5.3 Flash measured
SREBench (Vals AI)Not measured0.8%Only GLM 5.3 Flash measured
Finance Agent (Vals AI)Not measured57.9%Only GLM 5.3 Flash measured
Tax Agent Bench (Vals AI)Not measured31.6%Only GLM 5.3 Flash measured
Legal Research Bench (Vals AI)Not measured45.2%Only GLM 5.3 Flash measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured10.4%Only GLM 5.3 Flash measured
Excel Modeling Benchmark (Vals AI)Not measured55.9%Only GLM 5.3 Flash measured
Terminal-Bench-Science (Vals AI)Not measured2.9%Only GLM 5.3 Flash measured
APEX-AgentsNot measured52.8%Only GLM 5.3 Flash measured
Neither model has a result on the other 29 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
Reasoning benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
GPQA DiamondNot measured86.4%Only GLM 5.3 Flash measured
LiveBench reasoningNot measured77.6%Only GLM 5.3 Flash measured
MMMU Pro (Vals AI)Not measured86.0%Only GLM 5.3 Flash measured
GPQA Diamond (Artificial Analysis run)Not measured91.2%Only GLM 5.3 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured39.9%Only GLM 5.3 Flash measured
GPQA Diamond (Epoch AI run)Not measured90.2%Only GLM 5.3 Flash measured
ARC-AGINot measured91.0%Only GLM 5.3 Flash measured
ARC-AGI-2Not measured65.8%Only GLM 5.3 Flash measured
Chess puzzlesNot measured21.0%Only GLM 5.3 Flash measured
Mystery game puzzlesNot measured8.0%Only GLM 5.3 Flash measured
LMArena Text: hard promptsNot measured1490Only GLM 5.3 Flash measured
LMArena Text: expertNot measured1511Only GLM 5.3 Flash measured
LMArena Text: hard prompts in EnglishNot measured1488Only GLM 5.3 Flash measured
LMArena Vision: diagramsNot measured1317Only GLM 5.3 Flash measured
LMArena Vision: homeworkNot measured1318Only GLM 5.3 Flash measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
OTIS Mock AIMENot measured93.9%Only GLM 5.3 Flash measured
FrontierMath, tiers 1 to 3Not measured55.8%Only GLM 5.3 Flash measured
FrontierMath, tier 4Not measured17.1%Only GLM 5.3 Flash measured
ProofBenchNot measured21.0%Only GLM 5.3 Flash measured
LMArena Text: mathNot measured1503Only GLM 5.3 Flash measured
LMArena Text: mathematical workNot measured1497Only GLM 5.3 Flash measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Knowledge benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
MMLU ProNot measured86.1%Only GLM 5.3 Flash measured
LegalBench (Vals AI)Not measured83.9%Only GLM 5.3 Flash measured
TaxEval (Vals AI)Not measured75.6%Only GLM 5.3 Flash measured
LMArena Text: scienceNot measured1484Only GLM 5.3 Flash measured
LMArena Text: medicine and healthcareNot measured1475Only GLM 5.3 Flash measured
LMArena Text: legal and governmentNot measured1473Only GLM 5.3 Flash measured
LMArena Text: business and financeNot measured1460Only GLM 5.3 Flash measured
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
Design Arena: websitesNot measured1272Only GLM 5.3 Flash measured
Design Arena: UI componentsNot measured1316Only GLM 5.3 Flash measured
Design Arena: game devNot measured1278Only GLM 5.3 Flash measured
Design Arena: data vizNot measured1262Only GLM 5.3 Flash measured
Design Arena: 3DNot measured1316Only GLM 5.3 Flash measured
Design Arena: all code categoriesNot measured1282Only GLM 5.3 Flash measured
Design Arena: SVGNot measured1285Only GLM 5.3 Flash measured
Design Arena: ASCII artNot measured1267Only GLM 5.3 Flash measured
LiveBench designNot measured77.2%Only GLM 5.3 Flash measured
GeneralDirectional onlyPublic boards, shown as published, kept out of the index28 boards, none shared
General benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
Vals IndexNot measured50.9%Only GLM 5.3 Flash measured
LiveBench data analysisNot measured76.4%Only GLM 5.3 Flash measured
MedScribe (Vals AI)Not measured88.9%Only GLM 5.3 Flash measured
Long context reasoning (AA-LCR)Not measured80.0%Only GLM 5.3 Flash measured
Surface Evolver BenchNot measured52.5%Only GLM 5.3 Flash measured
LMArena TextNot measured1471Only GLM 5.3 Flash measured
LMArena Text: instruction followingNot measured1478Only GLM 5.3 Flash measured
LMArena Text: creative writingNot measured1441Only GLM 5.3 Flash measured
LMArena VisionNot measured1294Only GLM 5.3 Flash measured
LMArena Text: EnglishNot measured1474Only GLM 5.3 Flash measured
LMArena Text: non-EnglishNot measured1462Only GLM 5.3 Flash measured
LMArena Text: ChineseNot measured1531Only GLM 5.3 Flash measured
LMArena Text: GermanNot measured1462Only GLM 5.3 Flash measured
LMArena Text: JapaneseNot measured1444Only GLM 5.3 Flash measured
LMArena Text: KoreanNot measured1436Only GLM 5.3 Flash measured
LMArena Text: FrenchNot measured1491Only GLM 5.3 Flash measured
LMArena Text: SpanishNot measured1475Only GLM 5.3 Flash measured
LMArena Text: RussianNot measured1465Only GLM 5.3 Flash measured
LMArena Text: PolishNot measured1450Only GLM 5.3 Flash measured
LMArena Text: multi-turnNot measured1469Only GLM 5.3 Flash measured
LMArena Text: longer queriesNot measured1481Only GLM 5.3 Flash measured
LMArena Text: writing and languageNot measured1455Only GLM 5.3 Flash measured
LMArena Text: entertainment and mediaNot measured1440Only GLM 5.3 Flash measured
LMArena Vision: EnglishNot measured1295Only GLM 5.3 Flash measured
LMArena Vision: ChineseNot measured1363Only GLM 5.3 Flash measured
LMArena Vision: reading textNot measured1299Only GLM 5.3 Flash measured
LMArena Vision: humorNot measured1279Only GLM 5.3 Flash measured
LMArena Vision: creative writingNot measured1270Only GLM 5.3 Flash measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Devstral 2 2512 and GLM 5.3 Flash
BenchmarkDevstral 2 2512GLM 5.3 FlashLeader
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$0.0014Fits in one request
GLM 5.3 Flash$0.0004Fits in one request

GLM 5.3 Flash costs less

Repository review

50K input + 3K output tokens

Devstral 2 2512$0.026Fits in one request
GLM 5.3 Flash$0.0090Fits in one request

GLM 5.3 Flash costs less

Agent loop

200K input + 10K output tokens

Devstral 2 2512$0.100Fits in one request
GLM 5.3 Flash$0.035Fits in one request

GLM 5.3 Flash 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.

Specifications of Devstral 2 2512 and GLM 5.3 Flash
SpecificationMistral Devstral 2 2512Z.ai GLM 5.3 Flash
MakerMistral AIZ.ai
WeightsOpen weightsOpen weights
ReleasedDecember 9, 2025August 26, 2026
Context window262K1.05M
Input $/Mtok$0.40$0.15
Output $/Mtok$2.00$0.50
Coding indexNot benchmarked57.7
Independent measurements behind it16
Cost per solved task$1.19$0.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Devstral 2 2512 better than GLM 5.3 Flash for coding?

Only GLM 5.3 Flash has a coding score, 57.7 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, Devstral 2 2512 or GLM 5.3 Flash?

Devstral 2 2512 costs $0.40 per million input tokens and $2.00 per million output tokens; GLM 5.3 Flash costs $0.15 and $0.50. Per solved SWE-bench Verified task, Devstral 2 2512 costs $1.19 and GLM 5.3 Flash $0.02.

Which has the bigger context window, Devstral 2 2512 or GLM 5.3 Flash?

GLM 5.3 Flash, with 1.05M tokens against 262K.

How many benchmarks is the Devstral 2 2512 vs GLM 5.3 Flash comparison based on?

5 benchmarks have a result for both models as of October 22, 2026. Devstral 2 2512's coding index rests on 1 independent benchmark and GLM 5.3 Flash's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next