# Inkling-Small vs Spark-X2.6-4B

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

- Canonical page: https://benchlm.ai/compare/inkling-small-vs-spark-x2-6-4b
- Last updated: October 20, 2026

- Shared sourced benchmarks: 11
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Inkling-Small leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Inkling-Small has the higher overall point estimate 52.71 to 40.14. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 93.3 for Inkling-Small and 78.2 for Spark-X2.6-4B.
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 77.4% and 53.1%.
- Spark-X2.6-4B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Inkling-Small | Spark-X2.6-4B |
|----------|----------|----------|
| Creator | Thinking Machines Lab | SparkLLM |
| Type | Open Weight | Open Weight |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 1M |
| Overall Score | 52.71 | 40.14 |
| Benchmarks Covered | 28 | 20 |
| Pricing (input/output) | $0.58 / $1.44 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Inkling-Small public-lane score: 36.7 (Supported · #79/131)
- Spark-X2.6-4B public-lane score: 33 (Estimated · #89/131)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 64.7% | Coming soon | Coming soon |
| BrowseComp | 77.4% | 53.1% | Inkling-Small |
| MCP Atlas | 79.6% | 62.4% | Inkling-Small |
| Toolathlon-Verified | 54.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 55.1% | Coming soon | Coming soon |
| BFCL v4 | Coming soon | 71.8% | Coming soon |
| τ²-bench results | Coming soon | 86.9% | Coming soon |
| HLE w/ tools | Coming soon | 36.9% | Coming soon |
| τ³-bench results | Coming soon | 34.7% | Coming soon |
| Claw-Eval | Coming soon | 69.9% | Coming soon |

### Coding

- Winner: Directional only
- Inkling-Small public-lane score: 37.6 (Supported · #72/152)
- Spark-X2.6-4B public-lane score: 30.6 (Estimated · #95/152)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.2% | 62.8% | Inkling-Small |
| SWE-bench Pro | 55.9% | 54.3% | Inkling-Small |
| Terminal-Bench 2.1 | 64.7% | Coming soon | Coming soon |
| SciCode | 48.7% | 36.8% | Inkling-Small |
| LiveCodeBench (Vals) | 85.9% | Coming soon | Coming soon |
| SWE-bench (Vals) | 82.2% | Coming soon | Coming soon |
| SWE Multilingual | Coming soon | 64.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- Inkling-Small public-lane score: 55 (Unranked · 4 rankable rows)
- Spark-X2.6-4B public-lane score: 48.8 (Unranked · 2 rankable rows)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 40.1% | Coming soon | Coming soon |
| CritPt | 8.3% | Coming soon | Coming soon |
| ARC-AGI-1 | 84.00% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 53.3% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Inkling-Small public-lane score: 67.5 (#37/55)
- Spark-X2.6-4B public-lane score: Coming soon

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 74% | Coming soon | Coming soon |
| CharXiv | 81.3% | Coming soon | Coming soon |
| CharXiv w/o tools | 77.4% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Inkling-Small public-lane score: 54.8 (Supported · #63/187)
- Spark-X2.6-4B public-lane score: 43 (Estimated · #109/187)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.5% | 69.9% | Inkling-Small |
| GPQA-D | 89.5% | 77.1% | Inkling-Small |
| HLE | 47.8% | Coming soon | Coming soon |
| HLE w/o tools | 31.6% | 17.9% | Inkling-Small |
| GPQA Diamond (Vals) | 83.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 85.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Inkling-Small
- Inkling-Small public-lane score: 93.3 (#9/149)
- Spark-X2.6-4B public-lane score: 78.2 (#62/149)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 82.2% | 75.8% | Inkling-Small |
| IFEval | Coming soon | 93.6% | Coming soon |

### Mathematics

- Winner: Not comparable
- Inkling-Small public-lane score: 69.8 (#5/12)
- Spark-X2.6-4B public-lane score: 76.4 (Unranked · 3 rankable rows)

| Benchmark | Inkling-Small | Spark-X2.6-4B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.5% | 91.2% | Inkling-Small |
| HMMT Feb 2026 | 90.2% | 81.3% | Inkling-Small |
| FrontierMath v2 (Tiers 1-3) | 46.316% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 17.073% | Coming soon | Coming soon |
| IMOAnswerBench | Coming soon | 75.2% | Coming soon |

## FAQ

### Which is better overall, Inkling-Small or Spark-X2.6-4B?

Inkling-Small has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Inkling-Small and Spark-X2.6-4B?

The widest category gap is in instruction following, where the averages are 93.3 for Inkling-Small and 78.2 for Spark-X2.6-4B.

### How many benchmarks does Inkling-Small cover on BenchLM?

Inkling-Small currently has 28 sourced benchmark scores on BenchLM.

### How many benchmarks does Spark-X2.6-4B cover on BenchLM?

Spark-X2.6-4B currently has 20 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Inkling-Small vs Inkling](/compare/inkling-vs-inkling-small)
- [Spark-X2.6-4B vs Inkling](/compare/inkling-vs-spark-x2-6-4b)
- [Inkling-Small vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-inkling-small)
- [Spark-X2.6-4B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-spark-x2-6-4b)

## Explore More

- [Inkling-Small profile](/models/inkling-small)
- [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)