Spark-X2.6-4B
Explore Spark-X2.6-4B from SparkLLM: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.
Compare Spark-X2.6-4B with other models →Compare subscription plansExplore data coverage
Pricing · OpenRouter
No OpenRouter pricing is recorded for this model. Missing rates are not free.
Official / vendor benchmarks
Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| Average of 30 benchmarks (SparkLLM) | 63.3 scorehigh effort | All 1 recorded result & sources63.3 score · raw 63.3 score Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Average” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| BFCL v4 (overall) | 71.8%high effort | All 1 recorded result & sources71.8% · raw 71.8 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “BFCL-V4” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| τ²-bench (Tau-2) | 86.9%high effort | All 1 recorded result & sources86.9% · raw 86.9 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “τ²-bench” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| τ³-bench Banking | 34.7%high effort | All 1 recorded result & sources34.7% · raw 34.7 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “τ³-bench” in the card figure. Self-reported; run date unpublished. The 4B figure labels this τ³-bench; the 1.7B figure labels it τ³-bench Banking with the same 4B reference value. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| VitaBench 2.0 (SparkLLM) | 30.8%high effort | All 1 recorded result & sources30.8% · raw 30.8 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “VitaBench2.0” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| MCP Atlas | 62.4%high effort | All 1 recorded result & sources62.4% · raw 62.4 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “MCP-Atlas” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| EnterpriseOps-Gym (SparkLLM; run unspecified) | 33.6%high effort | All 1 recorded result & sources33.6% · raw 33.6 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “EnterpriseOps-Gym” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| ClawEval-EN (SparkLLM) | 69.9%high effort | All 1 recorded result & sources69.9% · raw 69.9 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “ClawEval-EN” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| BrowseComp | 53.1%high effort | All 1 recorded result & sources53.1% · raw 53.1 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “BrowseComp” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| SWebBench (SparkLLM in-house) | 71.7%high effort | All 1 recorded result & sources71.7% · raw 71.7 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “SWebBench” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| PAgentBench (SparkLLM in-house) | 74.1%high effort | All 1 recorded result & sources74.1% · raw 74.1 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “PAgentBench” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| SWE-bench Pro (revision unspecified) | 54.3%high effort | All 1 recorded result & sources54.3% · raw 54.3 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “SWE Pro” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| SWE-bench Verified | 62.8%high effort | All 1 recorded result & sources62.8% · raw 62.8 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “SWE Verified” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| SWE-bench Multilingual | 64.7%high effort | All 1 recorded result & sources64.7% · raw 64.7 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “SWE Multilingual” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| SciCode (SparkLLM; setup unspecified) | 36.8%high effort | All 1 recorded result & sources36.8% · raw 36.8 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “SciCode” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| Gaokao Math 2026 (SparkLLM, five papers out of 150) | 134.9 pointshigh effort | All 1 recorded result & sources134.9 points · raw 134.9 points Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Gaokao 2026” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| AIME 2026 | 91.2%high effort | All 1 recorded result & sources91.2% · raw 91.2 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “AIME 2026” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| HMMT February 2026 | 81.3%high effort | All 1 recorded result & sources81.3% · raw 81.3 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “HMMT Feb 26” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| IMO-AnswerBench (SparkLLM) | 75.2%high effort | All 1 recorded result & sources75.2% · raw 75.2 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “IMO-AnswerBench” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| AA-LCR v1.1 | 67.3%high effort | All 1 recorded result & sources67.3% · raw 67.3 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “AA-LCRv1.1” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| LongBench v2 | 53.3%high effort | All 1 recorded result & sources53.3% · raw 53.3 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “LongBench v2” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| GraphWalks BFS F1 (256K context) | 92.2 f1high effort | All 1 recorded result & sources92.2 f1 · raw 92.2 f1 Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Graphwalks bfs 256k f1” in the card figure. Self-reported; run date unpublished. F1 on a 0–100 scale, as the figure prints it. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| GraphWalks BFS F1 (1M context) | 34.2 f1high effort | All 1 recorded result & sources34.2 f1 · raw 34.2 f1 Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Graphwalks bfs 1m f1” in the card figure. Self-reported; run date unpublished. F1 on a 0–100 scale, as the figure prints it. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| MRCR 256K–512K | 65.6%high effort | All 1 recorded result & sources65.6% · raw 65.6 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Openai_MRCR v2 256k-512k” in the card figure. Self-reported; run date unpublished. Source label OpenAI MRCR v2; needle count unstated on the card. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| MRCR 512K–1M | 26%high effort | All 1 recorded result & sources26% · raw 26 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “Openai_MRCR v2 512k-1M” in the card figure. Self-reported; run date unpublished. Source label OpenAI MRCR v2; needle count unstated on the card. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| IFEval | 93.6%high effort | All 1 recorded result & sources93.6% · raw 93.6 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “IFEval” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| IFBench | 75.8%high effort | All 1 recorded result & sources75.8% · raw 75.8 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “IFBench” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| Humanity's Last Exam (no tools) | 17.9%high effort | All 1 recorded result & sources17.9% · raw 17.9 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “HLE(w/o tools)” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| Humanity's Last Exam (with tools) | 36.9%high effort | All 1 recorded result & sources36.9% · raw 36.9 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “HLE(w tools)” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| GPQA (SparkLLM; subset unstated) | 69.9%high effort | All 1 recorded result & sources69.9% · raw 69.9 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “GPQA” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
| GPQA Diamond | 77.1%high effort | All 1 recorded result & sources77.1% · raw 77.1 % Headline · high effort · Own vendor Source/record date: 2026-10-20 Harness: SparkLLM own run at thinking high per its card, temperature 1.0, top_p 0.95; exact label “GPQA Diamond” in the card figure. Self-reported; run date unpublished. https://huggingface.co/XHToken/Spark-X2.6-4B/resolve/aa074aa851209a683aeaf5f99a8e25a642d94541/images/all_benchmark.svg |
Independent evaluators
Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.
No independent evaluator results are recorded for this model.
Read how we select and source scores or the comparison guide.