Pairwise benchmark snapshot · Aug 16, 2026
In this head-to-head showdown, Claude Haiku 4.5 delivers higher overall intelligence and human-preferred responses (Elo 1,438 vs 1,320), while Claude Haiku 4.5 leads in SWE-bench software engineering benchmarks (58.2%), while Codestral 25.01 is more budget-friendly at $0.9/1M per 1M output tokens, while Claude Haiku 4.5 provides faster response streaming (175 tok/s). Review the complete breakdown below to determine which model best fits your performance and budget requirements.
10 direct benchmark disciplines evaluated across capability, speed, and cost
Anthropic cheap/fast Claude SKU. Official Claude Platform list price $1/$5 per 1M tokens (Anthropic Haiku page).
Mistral code-specialist model.
Currently comparing Claude Haiku 4.5 vs Codestral 25.01. Alternative family tiers available.
Δ 118 Arena Elo pts
175 tok/s
$0.9 / 1M output
Relative percentile scores computed across all active models in the benchmark catalog.
Comparing top Western standard models with China's leading frontier rival across 6 skill dimensions. Tap any spoke or dot to inspect.
Category wins across reasoning intelligence, generation speed, and token cost.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
| Benchmark | Claude Haiku 4.5 | Codestral 25.01 | Advantage Delta |
|---|---|---|---|
| Preference Elo | +118 | ||
| Coding Elo | +44 | ||
| LiveBench | +8.4% | ||
| SWE-bench | +6.4% | ||
| GPQA Diamond | +15.6% | ||
| Time to first token | +55 ms | ||
| Output speed | 175 tok/s | 148 tok/s | +27 tok/s |
| Input price | $0.3/1M | +$0.7/1M | |
| Output price | $0.9/1M | +$4.1/1M | |
| Context window | +56k |
Simulate monthly production API costs in USD (US Dollar).
Codestral 25.01 is estimated to save $86.00/month ($1,032/year).
Higher SWE-bench (58.2%).
Lower output list price ($0.9/1M).
Lower TTFT (95 ms).
Larger window (256k).
Claude Haiku 4.5 is the side marked multimodal in the catalog.
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | Claude Haiku 4.5 | Higher SWE-bench (58.2%). |
| High-volume chat | Codestral 25.01 | Lower output list price ($0.9/1M). |
| Voice / low-latency UI | Claude Haiku 4.5 | Lower TTFT (95 ms). |
| Long-document RAG | Codestral 25.01 | Larger window (256k). |
| Screenshots / vision | Claude Haiku 4.5 | Claude Haiku 4.5 is the side marked multimodal in the catalog. |
$1/$5 hosted Claude vs a cheap long-context open sibling. The alternative-to-Sonnet pair that is honest.
Huge window, cheap hosted lists. The Haiku alternative that is actually open-weight.
Official Anthropic list $1/$5. This is the SKU behind “cheapest Claude alternative” that is still Claude.
Jan 2025 code model. Still a valid cheap-coding compare. Not a chatbot.
No comments posted on this matchup yet. Be the first to share an evaluation note!
Dynamic OpenGraph banner generated at /compare/claude-haiku-4-5-vs-codestral-25/opengraph-image
Verified Head-to-Head Telemetry
compare · Aug 16, 2026
Haiku 4.5 vs Llama 4 Scout: cheap Claude versus cheap open Llama
launch · Apr 8, 2026
Llama 4 Scout: long-context open sibling of Maverick
launch · Oct 22, 2025
Claude Haiku 4.5 at $1/$5: the cheap Claude people actually ship
launch · Jan 14, 2025
Codestral 25.01: Mistral’s code-specialist row