Claude Haiku 4.5 vs Gemini 3.8 Flash
Choose two or three models. Copy the URL to share your selection.
| Comparison | Claude Haiku 4.5claude-haiku-4-5 | Gemini 3.8 Flashgemini-3.8-flash |
|---|---|---|
| Type | Chat | Chat |
| Best for | Fast, low-cost replies and high-volume everyday tasks | Fast, low-cost replies and high-volume everyday tasks |
| TokenRex price | $1.00 in / $5.00 out per 1M tokens | $0.75 in / $3.75 out per 1M tokens |
| Cached input / 1M tokens | $0.10 per 1M tokens | $0.075 per 1M tokens |
| Cache write / 1M tokens | $1.25 per 1M tokens | No extra fee |
| Cached output | Not offered · standard output rate applies | Not offered · standard output rate applies |
| Market price | $1.00 in / $5.00 out per 1M tokens | $0.75 in / $3.75 out per 1M tokens |
| Context window (provider) | 200,000 tokens | Not applicable |
| Input token limit (provider) | Within the context window | 1,048,576 tokens |
| Maximum output | 64,000 tokens | 65,536 tokens |
| Knowledge cutoff | Feb 2025 | — |
| Vendor input modalities | Text, Image | Not verified |
| Vendor output modalities | Text | Not verified |
| TokenRex endpoints | POST /v1/chat/completions · POST /v1/messages | POST /v1/chat/completions |
| TokenRex input | Text, Image/PDF content through the chat bridge | — |
| TokenRex output | Text | — |
| Benchmarks | ||
| Benchmark evidence | 1 source-linked results | 6 source-linked results |
| SWE-bench Verified | 73.3% Anthropic methodology footnote: simple bash+file-edit scaffold, averaged over 50 trials, no test-time compute, 128K thinking budget, default sampling, full 500-problem set, with a prompt addendum instructing heavy tool use. Haiku 4.5's catalog default is Extended thinking (no explicit low/medium/high effort knob), so this is treated as the base/default-thinking configuration, not a stripped-down no-thinking run. Anthropic · Introducing Claude Haiku 4.5 | 80% Vals AI independent evaluation, default configuration. Published source text: SWE-bench (Verified) Vals AI | 80.00% | 18 of 23 | 24 of 88 AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology) |
| GPQA Diamond | — | 94.44% Vals AI independent evaluation, default model configuration, dated post-Sept 2, 2026 GA launch. Published source text: GPQA Diamond Vals AI | 94.44% | 4 of 23 | 4 of 138 | Leader Gemini 3.1 Pro | 1.01 pts behind AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology) |
| Terminal-Bench 2.1 | — | 89.4% Terminus 2 default agent harness, high effort, Sept 2026 GA launch per Google model card / Google evals-methodology page. Published source text: Terminal-Bench 2.1 89.4% (Terminus 2 harness) Wait Which Model – Gemini 3.8 Flash |
| Humanity's Last Exam | — | 54.9% High effort/thinking setting, Sept 2026 GA launch. Published source text: Humanity's Last Exam 54.9% Wait Which Model – Gemini 3.8 Flash |
| FrontierCode v1.1 (Extended) | — | 53.45% Cognition FrontierCode 1.1; Gemini 3.8 Flash; medium effort; chisel harness; Extended subset (150 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.5345. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget. Cognition · FrontierCode 1.1 original leaderboard |
| FrontierCode v1.1 (Main) | — | 41.19% Cognition FrontierCode 1.1; Gemini 3.8 Flash; medium effort; chisel harness; Main subset (100 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.4119. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget. Cognition · FrontierCode 1.1 original leaderboard |
No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.
— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.
Claude Haiku 4.5
Sources and verification
Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.
- Provider model specifications
Vendor-reported
Last checked - Anthropic · Introducing Claude Haiku 4.5
Vendor-reported
Last checked
Research notes (1)
- Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.
Gemini 3.8 Flash
Sources and verification
Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.
- Provider model specifications
Vendor-reported
Last checked - AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology)
Third-party report
Last checked - Wait Which Model – Gemini 3.8 Flash
Third-party report
Last checked - Cognition · FrontierCode 1.1 original leaderboard
Third-party report
Last checked
Research notes (1)
- Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.
Popular comparisons
- GPT-6 Sol vs Claude Opus 5.5
- GPT-6 Sol vs Gemini 4 Argon
- Claude Opus 5.5 vs Gemini 4 Argon
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6 Astra vs Claude Sonnet 5
- GPT-6 Astra vs Gemini 3.1 Pro
- Claude Sonnet 5 vs Gemini 3.1 Pro
- Claude Opus 5.5 vs Claude Sonnet 5
- GPT-5.5 vs Claude Sonnet 5
- GPT-5.5 vs Gemini 2.5 Pro
- GPT-5 vs Gemini 2.5 Pro
- GPT-6 Luna vs Gemini 3.8 Flash
- Claude Haiku 4.5 vs Gemini 3.8 Flash
- GPT-5 Mini vs Gemini 2.5 Flash
- GPT-5 Nano vs Gemini 2.5 Flash Lite
- GPT-5.4 Mini vs Claude Haiku 4.5