# Mistral Medium 3.5 128B vs Spark-X2.6-4B

> Side-by-side benchmark comparison for Mistral Medium 3.5 128B and Spark-X2.6-4B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mistral-medium-3-5-128b-vs-spark-x2-6-4b
- Last updated: October 20, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Mistral Medium 3.5 128B and Spark-X2.6-4B share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Spark-X2.6-4B has the lower published output-token price.
- Spark-X2.6-4B has the larger published context window at 1M.

## Model Snapshot

| Property | Mistral Medium 3.5 128B | Spark-X2.6-4B |
|----------|----------|----------|
| Creator | Mistral | SparkLLM |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1M |
| Independent public score (not head-to-head) | 33.56 | 40.14 |
| Benchmarks Covered | 7 | 20 |
| Pricing (input/output) | $1.50 / $7.50 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 19.9 (Supported · #112/131)
- Spark-X2.6-4B public-lane score: 33 (Estimated · #89/131)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| τ³-bench results | 91.4% | 34.7% | Mistral Medium 3.5 128B |
| Gert Labs | 39.10% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 39.0% | Coming soon | Coming soon |
| BFCL v4 | Coming soon | 71.8% | Coming soon |
| τ²-bench results | Coming soon | 86.9% | Coming soon |
| MCP Atlas | Coming soon | 62.4% | Coming soon |
| BrowseComp | Coming soon | 53.1% | Coming soon |
| HLE w/ tools | Coming soon | 36.9% | Coming soon |
| Claw-Eval | Coming soon | 69.9% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 22.6 (Estimated · #116/152)
- Spark-X2.6-4B public-lane score: 30.6 (Estimated · #95/152)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | 62.8% | Mistral Medium 3.5 128B |
| SWE-bench (Vals) | 66.4% | Coming soon | Coming soon |
| SWE-bench Pro | Coming soon | 54.3% | Coming soon |
| SWE Multilingual | Coming soon | 64.7% | Coming soon |
| SciCode | Coming soon | 36.8% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 72.6 (Unranked · 2 rankable rows)
- Spark-X2.6-4B public-lane score: 48.8 (Unranked · 2 rankable rows)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 53.3% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 60.1 (Unranked · 1 rankable row)
- Spark-X2.6-4B public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 31.8 (Supported · #151/187)
- Spark-X2.6-4B public-lane score: 43 (Estimated · #109/187)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 34.8% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 75.3% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 77.1% | Coming soon |
| HLE w/o tools | Coming soon | 17.9% | Coming soon |
| GPQA | Coming soon | 69.9% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: 84 (#52/149)
- Spark-X2.6-4B public-lane score: 78.2 (#62/149)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 93.6% | Coming soon |
| IFBench | Coming soon | 75.8% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Mistral Medium 3.5 128B public-lane score: Coming soon
- Spark-X2.6-4B public-lane score: 76.4 (Unranked · 3 rankable rows)

| Benchmark | Mistral Medium 3.5 128B | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | Coming soon | 91.2% | Coming soon |
| HMMT Feb 2026 | Coming soon | 81.3% | Coming soon |
| IMOAnswerBench | Coming soon | 75.2% | Coming soon |

## FAQ

### Is there enough evidence to pick between Mistral Medium 3.5 128B and Spark-X2.6-4B?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Mistral Medium 3.5 128B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-mistral-medium-3-5-128b)
- [Spark-X2.6-4B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-spark-x2-6-4b)
- [Mistral Medium 3.5 128B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-mistral-medium-3-5-128b)
- [Spark-X2.6-4B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-spark-x2-6-4b)

## Explore More

- [Mistral Medium 3.5 128B profile](/models/mistral-medium-3-5-128b)
- [Spark-X2.6-4B profile](/models/spark-x2-6-4b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)