Pairwise benchmark snapshot · Aug 17, 2026noindex (thin pair)

Mistral: Mistral Small 3.1 24B vs Yi-Lightning benchmark

Name: Mistral: Mistral Small 3.1 24B vs Yi-Lightning AI benchmark comparison
Creator: CompareLLM
License: https://creativecommons.org/licenses/by/4.0/

In this head-to-head showdown, Yi-Lightning is more budget-friendly at $0.14/1M per 1M output tokens. Review the complete breakdown below to determine which model best fits your performance and budget requirements.

Share Analysis:Share:

WhatsApp Telegram X LinkedIn

Executive Verdict Summary

Yi-Lightning holds empirical advantage (2 of 3 metrics)

Coding / SWESWE-bench

Yi-LightningTop code solve rate

ReasoningGPQA / Live

Yi-LightningTop logical accuracy

Best Value$/1M Tok

Yi-LightningLowest API billing cost

Speed / TokTok/Sec

Yi-LightningFastest stream rate

Verified Advantage Breakdown

3 benchmarks evaluated across capability, speed, and cost

Mistral: Mistral Small 3.1 24B (1)Yi-Lightning (2)

Mistral: Mistral Small 3.1 24B

1 of 3 Wins

✓Context window

Yi-Lightning

2 of 3 Wins

✓Input price✓Output price

Mistral

Leads 1 of 3

Mistral: Mistral Small 3.1 24B

Auto-discovered from OpenRouter (mistralai/mistral-small-3.1-24b-instruct). Preview until a second source matches.

In: $0.351 · Out: $0.555/1M

01.AI

Leads 2 of 3

Yi-Lightning

01.AI ultra-fast reasoning model delivering top LiveBench efficiency.

LightningElo 1,475In: $0.14 · Out: $0.14/1M

Top Rival Showdowns for Mistral: Mistral Small 3.1 24B

All Matchups

Compare vs:vs Claude Opus 4.5 vs GPT-5 vs Gemini 3 Pro vs Grok 4.6 vs DeepSeek V4 Pro

Preference Leader

No shared data

Single model data

Throughput Leader

No shared data

No latency data

Value per Dollar LeaderYi-Lightning Wins

Yi-Lightning

$0.14 / 1M output

Capability Percentiles

Relative percentile scores computed across all active models in the benchmark catalog.

Multi-Dimensional Capability Radar

Leaders Matchup Capability Radar

Comparing top standard models across 6 key capability dimensions. Tap any spoke or dot to inspect.

Tap any node to inspect

0–100 %ile

Overall Matchup Breakdown

Category wins across reasoning intelligence, generation speed, and token cost.

Mistral: Mistral Small 3.1 24B (1)vsYi-Lightning (9)

Mistral: Mistral Small 3.1 24B: 1W (10%)Yi-Lightning: 9W (90%)

← Mistral: Mistral Small 3.1 24BYi-Lightning →

🏆Yi-Lightning Leads(5/5)

Intelligence & Reasoning

Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy

Benchmark

Mistral: Mistral Small 3.1 24BvsYi-Lightning

Preference Elo

—vs1,475

Coding Elo

—vs1,480

SWE-bench

—vs63.4%

LiveBench

—vs65%

GPQA Diamond

—vs78%

Mistral: Mistral Small 3.1 24B: 0WYi-Lightning: 5W

🏆Yi-Lightning Leads(2/2)

Speed & Latency

Generation throughput and time to first token responsiveness

Benchmark

Mistral: Mistral Small 3.1 24BvsYi-Lightning

Output speed

—vs130 tok/s

Time to first token

—vs150 ms

Mistral: Mistral Small 3.1 24B: 0WYi-Lightning: 2W

🏆Yi-Lightning Leads(2/3)

Pricing & Capacity

Cost per million tokens and max context window length

Benchmark

Mistral: Mistral Small 3.1 24BvsYi-Lightning

Output price

$0.555/1Mvs$0.14/1M+$0.415/1M

Input price

$0.351/1Mvs$0.14/1M+$0.211/1M

Context window

128kvs16k+112k

Mistral: Mistral Small 3.1 24B: 1WYi-Lightning: 2W

Side-by-Side Benchmark Matrix

Mistral: Mistral Small 3.1 24BYi-Lightning

Preference Elo

Mistral: Mistral Small 3.1 24B—

Yi-Lightning1,475

Coding Elo

Mistral: Mistral Small 3.1 24B—

Yi-Lightning1,480

LiveBench

Mistral: Mistral Small 3.1 24B—

Yi-Lightning65%

SWE-bench

Mistral: Mistral Small 3.1 24B—

Yi-Lightning63.4%

GPQA Diamond

Mistral: Mistral Small 3.1 24B—

Yi-Lightning78%

Time to first token

Mistral: Mistral Small 3.1 24B—

Yi-Lightning150 ms

Output speed

Mistral: Mistral Small 3.1 24B—

Yi-Lightning130 tok/s

Input priceYi-Lightning +$0.211/1M

Mistral: Mistral Small 3.1 24B$0.351/1M

Yi-Lightning$0.14/1M

Output priceYi-Lightning +$0.415/1M

Mistral: Mistral Small 3.1 24B$0.555/1M

Yi-Lightning$0.14/1M

Context windowMistral: Mistral Small 3.1 24B +112k

Mistral: Mistral Small 3.1 24B128k

Yi-Lightning16k

Benchmark	Mistral: Mistral Small 3.1 24B	Yi-Lightning	Advantage Delta
Preference Elo	—	1,475 lmarena · Aug 17, 2026	—
Coding Elo	—	1,480 lmarena · Aug 17, 2026	—
LiveBench	—	65% livebench · Aug 17, 2026	—
SWE-bench	—	63.4% swebench · Aug 17, 2026	—
GPQA Diamond	—	78% seed-bootstrap · Aug 1, 2026	—
Time to first token	—	150 ms seed-bootstrap · Aug 1, 2026	—
Output speed	—	130 tok/s seed-bootstrap · Aug 1, 2026	—
Input price	$0.351/1M openrouter · Aug 17, 2026	$0.14/1M seed-bootstrap · Aug 1, 2026	+$0.211/1M
Output price	$0.555/1M openrouter · Aug 17, 2026	$0.14/1M seed-bootstrap · Aug 1, 2026	+$0.415/1M
Context window	128k openrouter · Aug 17, 2026	16k seed-bootstrap · Aug 1, 2026	+112k

Workload Cost & Savings Calculator

Simulate monthly production API costs in USD (US Dollar).

Save 66% with Yi-Lightning

Monthly Volume50M tokens/mo

Quick Presets:

Token Ratio (In vs Out)70% In / 30% Out

RAG / Search (10% out)Coding / Chat (50% out)

Mistral: Mistral Small 3.1 24B$20.61 / mo

In: $12.29Out: $8.33

Yi-Lightning$7.00 / mo

In: $4.9Out: $2.1

Estimated Cost Delta

Yi-Lightning is estimated to save $13.61/month ($163/year).

Based on 50M tokens (30% gen)

Key Selection Recommendations

1
Yi-Lightning:Pick Yi-Lightning when you are optimizing output cost.

Recommended Workload Routing

Repo / coding agentsinsufficient data

Need SWE-bench on both sides.

High-volume chatYi-Lightning

Lower output list price ($0.14/1M).

Voice / low-latency UIinsufficient data

Need TTFT on both sides.

Long-document RAGMistral: Mistral Small 3.1 24B

Larger window (128k).

Screenshots / visionYi-Lightning

Yi-Lightning is the side marked multimodal in the catalog.

Target Workload	Recommended Pick	Evaluation Rationale
Repo / coding agents	insufficient data	Need SWE-bench on both sides.
High-volume chat	Yi-Lightning	Lower output list price ($0.14/1M).
Voice / low-latency UI	insufficient data	Need TTFT on both sides.
Long-document RAG	Mistral: Mistral Small 3.1 24B	Larger window (128k).
Screenshots / vision	Yi-Lightning	Yi-Lightning is the side marked multimodal in the catalog.

Cast Your Matchup Vote

0 total votes

Community Discussions (0)

No comments posted on this matchup yet. Be the first to share an evaluation note!

Social Share Card Preview

Dynamic OpenGraph banner generated at /compare/mistral-small-3-1-24b-instruct-vs-yi-lightning/opengraph-image

Save PNG

CompareLLM AI Matrix

Verified Head-to-Head Telemetry

LIVE BENCHMARK

Mistral

Mistral: Mistral Small 3.1 24B

Elo n/a

SWE-bench—

Speed (tok/s)128k

Input / 1M Tokens$0.351/1M

Output / 1M Tokens$0.555/1M

01.AI

Yi-Lightning

Elo 1,475

SWE-bench63.4%

Speed (tok/s)130 tok/s

Input / 1M Tokens$0.14/1M

Output / 1M Tokens$0.14/1M

Frequently Asked Questions

Which is better overall, Mistral: Mistral Small 3.1 24B or Yi-Lightning?: We do not have preference Elo for both models, so we do not declare an overall winner. Compare the metrics that exist.
Which is better at coding, Mistral: Mistral Small 3.1 24B or Yi-Lightning?: SWE-bench is missing for at least one model, so we do not rank coding from a single number.
Which is cheaper to run in production?: Yi-Lightning output tokens are $0.14/1M versus $0.555/1M. Input prices and retry rates still move the real bill.
Which is faster, Mistral: Mistral Small 3.1 24B or Yi-Lightning?: We do not have TTFT for both models.
Which has the larger context window?: Mistral: Mistral Small 3.1 24B accepts 128k tokens versus 16k.
Can I self-host either model?: Neither model is marked open-weights here. You are comparing hosted APIs.
Are these scores from CompareLLM’s own evals?: No. V1 aggregates public leaderboards (and optional first-party latency pings). Each cell names its source and date. Read /methodology.
What does preference Elo mean on this page?: Preference Elo is a crowd vote from LMArena / Arena. People see two hidden answers and pick the one they like more. The model that wins more often gets a higher Elo. That means people preferred it — not that it passed a school test. It is not SWE-bench, not accuracy, and not a number we invent. Mistral: Mistral Small 3.1 24B and Yi-Lightning Elo cells are dated snapshots from the named source — we do not compute Arena ourselves.

Similar Head-to-Head Comparisons

All Mistral: Mistral Small 3.1 24B matchups →|All Yi-Lightning matchups →

Yi-Lightning vs Yi-Large (previous other)Yi-Lightning vs Ernie 4.5 Turbo (next other)Mistral Large 3 vs Yi-Lightning Codestral 25.01 vs Yi-Lightning Claude Opus 4.5 vs Yi-Lightning Claude Opus 4.6 vs Yi-Lightning

Capability Percentiles

Relative percentile scores computed across all active models in the benchmark catalog.

Multi-Dimensional Capability Radar

Leaders Matchup Capability Radar

Comparing top standard models across 6 key capability dimensions. Tap any spoke or dot to inspect.

Tap any node to inspect

0–100 %ile

Side-by-Side Benchmark Matrix

Mistral: Mistral Small 3.1 24BYi-Lightning

Preference Elo

Mistral: Mistral Small 3.1 24B—

Yi-Lightning1,475

Coding Elo

Mistral: Mistral Small 3.1 24B—

Yi-Lightning1,480

LiveBench

Mistral: Mistral Small 3.1 24B—

Yi-Lightning65%

SWE-bench

Mistral: Mistral Small 3.1 24B—

Yi-Lightning63.4%

GPQA Diamond

Mistral: Mistral Small 3.1 24B—

Yi-Lightning78%

Time to first token

Mistral: Mistral Small 3.1 24B—

Yi-Lightning150 ms

Output speed

Mistral: Mistral Small 3.1 24B—

Yi-Lightning130 tok/s

Input priceYi-Lightning +$0.211/1M

Mistral: Mistral Small 3.1 24B$0.351/1M

Yi-Lightning$0.14/1M

Output priceYi-Lightning +$0.415/1M

Mistral: Mistral Small 3.1 24B$0.555/1M

Yi-Lightning$0.14/1M

Context windowMistral: Mistral Small 3.1 24B +112k

Mistral: Mistral Small 3.1 24B128k

Yi-Lightning16k

Benchmark

Mistral: Mistral Small 3.1 24B

Yi-Lightning

Advantage Delta

Preference Elo

—

1,475

lmarena · Aug 17, 2026

—

Coding Elo

—

1,480

lmarena · Aug 17, 2026

—

LiveBench

—

65%

livebench · Aug 17, 2026

—

SWE-bench

—

63.4%

swebench · Aug 17, 2026

—

GPQA Diamond

—

78%

seed-bootstrap · Aug 1, 2026

—

Time to first token

—

150 ms

seed-bootstrap · Aug 1, 2026

—

Output speed

—

130 tok/s

seed-bootstrap · Aug 1, 2026

—

Input price

$0.351/1M

openrouter · Aug 17, 2026

$0.14/1M

seed-bootstrap · Aug 1, 2026

+$0.211/1M

Output price

$0.555/1M

openrouter · Aug 17, 2026

$0.14/1M

seed-bootstrap · Aug 1, 2026

+$0.415/1M

Context window

128k

openrouter · Aug 17, 2026

16k

seed-bootstrap · Aug 1, 2026

+112k

Recommended Workload Routing

Repo / coding agentsinsufficient data

Need SWE-bench on both sides.

High-volume chatYi-Lightning

Lower output list price ($0.14/1M).

Voice / low-latency UIinsufficient data

Need TTFT on both sides.

Long-document RAGMistral: Mistral Small 3.1 24B

Larger window (128k).

Screenshots / visionYi-Lightning

Yi-Lightning is the side marked multimodal in the catalog.

Target Workload	Recommended Pick	Evaluation Rationale
Repo / coding agents	insufficient data	Need SWE-bench on both sides.
High-volume chat	Yi-Lightning	Lower output list price ($0.14/1M).
Voice / low-latency UI	insufficient data	Need TTFT on both sides.
Long-document RAG	Mistral: Mistral Small 3.1 24B	Larger window (128k).
Screenshots / vision	Yi-Lightning	Yi-Lightning is the side marked multimodal in the catalog.

Frequently Asked Questions

Which is better overall, Mistral: Mistral Small 3.1 24B or Yi-Lightning?

We do not have preference Elo for both models, so we do not declare an overall winner. Compare the metrics that exist.

Which is better at coding, Mistral: Mistral Small 3.1 24B or Yi-Lightning?

SWE-bench is missing for at least one model, so we do not rank coding from a single number.

Which is cheaper to run in production?

Yi-Lightning output tokens are $0.14/1M versus $0.555/1M. Input prices and retry rates still move the real bill.

Which is faster, Mistral: Mistral Small 3.1 24B or Yi-Lightning?

We do not have TTFT for both models.

Which has the larger context window?

Mistral: Mistral Small 3.1 24B accepts 128k tokens versus 16k.

Can I self-host either model?

Neither model is marked open-weights here. You are comparing hosted APIs.

Are these scores from CompareLLM’s own evals?

No. V1 aggregates public leaderboards (and optional first-party latency pings). Each cell names its source and date. Read /methodology.

What does preference Elo mean on this page?

Preference Elo is a crowd vote from LMArena / Arena. People see two hidden answers and pick the one they like more. The model that wins more often gets a higher Elo. That means people preferred it — not that it passed a school test. It is not SWE-bench, not accuracy, and not a number we invent. Mistral: Mistral Small 3.1 24B and Yi-Lightning Elo cells are dated snapshots from the named source — we do not compute Arena ourselves.